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

    Neuronpedia

    INDEX
    Explanations

    said/told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    思考
    -0.07
    .<
    -0.07
    .W
    -0.07
    bucket
    -0.06
    	P
    -0.06
    _QUAL
    -0.06
     AP
    -0.06
    CLUDE
    -0.06
    _tb
    -0.06
    awaiter
    -0.06
    POSITIVE LOGITS
     особенно
    0.07
     основе
    0.07
    νό
    0.06
     vigor
    0.06
     Bloss
    0.06
     invers
    0.06
    reich
    0.06
     lows
    0.06
     congest
    0.06
     sem
    0.06
    Act Density 0.036%

    No Known Activations