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

    Neuronpedia

    INDEX
    Explanations

    phone calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ier
    -0.07
     sigmoid
    -0.07
    流浪
    -0.07
    涼
    -0.06
    igg
    -0.06
     Convention
    -0.06
    草原
    -0.06
    egal
    -0.06
     evid
    -0.06
     Estr
    -0.06
    POSITIVE LOGITS
     humorous
    0.07
    淡淡
    0.07
    -token
    0.07
    (Integer
    0.07
    /types
    0.07
     ''}↵
    0.07
    _Null
    0.07
    ți
    0.07
    _numbers
    0.07
    (nodes
    0.07
    Act Density 0.112%

    No Known Activations