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

    Neuronpedia

    INDEX
    Explanations

    folks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [$_
    -0.07
    灰
    -0.07
    Ready
    -0.07
     keys
    -0.07
    _barang
    -0.07
     harmonic
    -0.07
    悲
    -0.06
     conn
    -0.06
     stabbing
    -0.06
    war
    -0.06
    POSITIVE LOGITS
     folks
    0.19
     folk
    0.08
     foes
    0.07
     Fol
    0.07
    ls
    0.07
    Vals
    0.06
    ocos
    0.06
     Pols
    0.06
    .vaadin
    0.06
     Рез
    0.06
    Act Density 0.002%

    No Known Activations