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

    Neuronpedia

    INDEX
    Explanations

    references to specific information or instructions

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

    look at this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.57
     Infórmanos
    -0.56
    DIPSETTING
    -0.56
     CanadaChoose
    -0.53
    sizeCache
    -0.51
    Географиясе
    -0.47
     defaultstate
    -0.47
     Taktlose
    -0.45
     gyhoeddwyd
    -0.45
    AddTagHelper
    -0.45
    POSITIVE LOGITS
     cursor
    0.45
    viser
    0.45
    ✨:
    0.45
    OFFER
    0.44
     évidence
    0.44
     flipped
    0.42
    داری
    0.42
    obacz
    0.42
     evidence
    0.42
     Offered
    0.41
    Act Density 0.017%

    No Known Activations