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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     datasets
    -0.08
     NIGHT
    -0.07
    .IsNull
    -0.07
    criteria
    -0.06
     eternity
    -0.06
    .proj
    -0.06
     kg
    -0.06
    珈
    -0.06
     sanitation
    -0.06
     accommodation
    -0.06
    POSITIVE LOGITS
    ?</
    0.07
    '](
    0.07
    illé
    0.07
    並不
    0.07
    ḣ
    0.07
    /block
    0.06
    款项
    0.06
    .getStart
    0.06
    _VARIABLE
    0.06
    abler
    0.06
    Act Density 0.001%

    No Known Activations