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

    Neuronpedia

    INDEX
    Explanations

    rules and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pressured
    -0.07
    engers
    -0.07
    ambda
    -0.07
    ρθ
    -0.06
     ニ
    -0.06
     Developing
    -0.06
    ponge
    -0.06
    .Test
    -0.06
     insp
    -0.06
     Mock
    -0.06
    POSITIVE LOGITS
    �
    0.06
    ء
    0.06
    Cong
    0.06
     thọ
    0.06
    _AREA
    0.06
    ůl
    0.06
    育
    0.06
     ekran
    0.06
     IMessage
    0.06
    .OrdinalIgnoreCase
    0.06
    Act Density 0.019%

    No Known Activations