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

    Neuronpedia

    INDEX
    Explanations

    communication of ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (card
    -0.06
    alic
    -0.06
    sti
    -0.06
    уж
    -0.06
     Lies
    -0.06
    атар
    -0.06
    .ak
    -0.06
    cock
    -0.06
    -office
    -0.06
    \Query
    -0.06
    POSITIVE LOGITS
    调查
    0.06
     subtype
    0.06
     tục
    0.06
    TRANS
    0.06
    _inner
    0.06
     sabotage
    0.06
     ='
    0.06
     های
    0.06
     Abstract
    0.06
    idlo
    0.06
    Act Density 0.040%

    No Known Activations