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

    Neuronpedia

    INDEX
    Explanations

    SOFTWARE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .f
    -0.06
    Invariant
    -0.06
     Nested
    -0.06
    nested
    -0.06
    TextInput
    -0.06
     Phrase
    -0.06
    _mark
    -0.06
    этому
    -0.06
    Facebook
    -0.06
    єв
    -0.06
    POSITIVE LOGITS
     discontent
    0.07
     Gerard
    0.07
    soever
    0.07
    INT
    0.07
     PER
    0.06
    يرا
    0.06
    ercial
    0.06
     беременности
    0.06
    aceous
    0.06
    ]==
    0.06
    Act Density 0.001%

    No Known Activations