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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kud
    -0.07
     수
    -0.07
    _exc
    -0.07
     زی
    -0.06
    ellido
    -0.06
     retreat
    -0.06
    -chain
    -0.06
    (userInfo
    -0.06
     tea
    -0.06
     executives
    -0.06
    POSITIVE LOGITS
    omatic
    0.07
     Περι
    0.07
    ceph
    0.07
    ural
    0.07
     Advertisement
    0.06
    kinson
    0.06
    genden
    0.06
    ظٹ
    0.06
    ----</
    0.06
    CLAIM
    0.06
    Act Density 0.003%

    No Known Activations