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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )!=
    -0.07
    JKLMNOP
    -0.06
    ानत
    -0.06
     Capital
    -0.06
     hesitate
    -0.06
    ."),
    -0.06
     guess
    -0.06
    some
    -0.06
     contractor
    -0.06
     sost
    -0.06
    POSITIVE LOGITS
     conservation
    0.07
     Stephanie
    0.07
    ↵
↵
↵
    0.07
    找
    0.06
    ány
    0.06
    كييف
    0.06
    时
    0.06
     OnTriggerEnter
    0.06
     {-
    0.06
    _mot
    0.06
    Act Density 0.000%

    No Known Activations