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

    Neuronpedia

    INDEX
    Explanations

    possessions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IO
    -0.08
    �
    -0.07
    roken
    -0.06
    handle
    -0.06
    NOP
    -0.06
     P
    -0.06
    .Draw
    -0.06
    로드
    -0.06
    ILER
    -0.06
     sincer
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.07
    减
    0.06
    城
    0.06
    -striped
    0.06
    学习
    0.06
     tumblr
    0.06
     Mental
    0.06
    순
    0.06
     grazing
    0.06
    使
    0.06
    Act Density 0.008%

    No Known Activations