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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly in structured data contexts

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

    assigned parameter values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.53
     Conſ
    -0.52
     Eſ
    -0.51
     eſſ
    -0.51
     ſta
    -0.49
     ſtate
    -0.48
     diſt
    -0.47
     paſſ
    -0.46
     tranſ
    -0.45
     ſch
    -0.45
    POSITIVE LOGITS
     value
    1.16
    value
    1.05
     Value
    0.82
     VALUE
    0.75
     propOrder
    0.73
     Wert
    0.66
    Value
    0.66
     valeur
    0.65
    VALUE
    0.64
     wartość
    0.62
    Act Density 0.006%

    No Known Activations