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

    Neuronpedia

    INDEX
    Explanations

    lib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izados
    -0.07
    (Location
    -0.07
    Que
    -0.06
    moduleId
    -0.06
    ensity
    -0.06
     poste
    -0.06
     часов
    -0.06
    .ne
    -0.06
     Virgin
    -0.06
    ophile
    -0.06
    POSITIVE LOGITS
    611
    0.07
     launching
    0.06
    τας
    0.06
    nock
    0.06
     看
    0.06
     gsl
    0.06
    _active
    0.06
     ổ
    0.06
     Bạn
    0.06
    _DEF
    0.06
    Act Density 0.005%

    No Known Activations