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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ичного
    -0.08
     ،
    -0.06
     centro
    -0.06
    -wise
    -0.06
    ils
    -0.06
    ulu
    -0.06
    ronics
    -0.06
    Emily
    -0.06
    _rand
    -0.06
    ruptions
    -0.05
    POSITIVE LOGITS
     maintain
    0.07
    ')");↵
    0.07
    错
    0.07
    (InitializedTypeInfo
    0.07
     that
    0.07
     cherish
    0.06
     sắt
    0.06
     On
    0.06
     UK
    0.06
    assertTrue
    0.06
    Act Density 0.621%

    No Known Activations