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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    事业单位
    -0.08
    kin
    -0.07
    simulation
    -0.07
    ity
    -0.07
    Transport
    -0.07
    _MOD
    -0.07
    letion
    -0.07
    Property
    -0.06
     atoms
    -0.06
    _man
    -0.06
    POSITIVE LOGITS
     quickest
    0.07
    시간
    0.07
    愔
    0.07
    _',
    0.07
    ----------------------------------------------------------------------------
    0.07
    ']+
    0.07
    /tests
    0.07
    はず
    0.07
     snippet
    0.06
    .other
    0.06
    Act Density 0.128%

    No Known Activations