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

    Neuronpedia

    INDEX
    Explanations

    oppose/against

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wheels
    -0.07
    닥
    -0.07
     revenge
    -0.07
    签订
    -0.07
    ogany
    -0.07
    ❁
    -0.07
    .IsDBNull
    -0.07
    嚏
    -0.07
     datingside
    -0.06
    $errors
    -0.06
    POSITIVE LOGITS
    Opts
    0.07
     <--
    0.07
    .annotation
    0.07
    слав
    0.07
    嗓子
    0.07
     traces
    0.07
    .source
    0.07
     Pump
    0.07
     translates
    0.06
    ':
    0.06
    Act Density 0.021%

    No Known Activations