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

    Neuronpedia

    INDEX
    Explanations

    word usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rx
    -0.07
    нами
    -0.07
     completion
    -0.07
    .getStatus
    -0.06
    _clip
    -0.06
     cascade
    -0.06
    pst
    -0.06
     wikipedia
    -0.06
    ,float
    -0.06
     villages
    -0.06
    POSITIVE LOGITS
     prostřed
    0.06
    زة
    0.06
    poon
    0.06
    OUTH
    0.06
     tỷ
    0.06
     profess
    0.06
     stere
    0.06
     referring
    0.06
     beide
    0.06
     организации
    0.06
    Act Density 0.038%

    No Known Activations