Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of food types and their quality in restaurant reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding a comma, "to", or number

    np_acts-logits-general · gemini-2.0-flash

    decision denying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cref
    -0.53
     MessageBoxIcon
    -0.52
    SideBar
    -0.52
     portátiles
    -0.51
    很高
    -0.51
    endswith
    -0.50
    ništ
    -0.49
    thenReturn
    -0.48
     destinés
    -0.48
    occuper
    -0.48
    POSITIVE LOGITS
     חיצוניים
    0.59
     blackened
    0.59
     strawberry
    0.56
    存于互联网档案馆
    0.55
     signature
    0.54
     blueberry
    0.54
     rosemary
    0.53
     triple
    0.52
     honey
    0.52
    fjspx
    0.52
    Act Density 0.116%

    No Known Activations