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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NASDAQ
    -0.06
    Clark
    -0.06
    せ
    -0.06
    消
    -0.06
    Amount
    -0.06
    branches
    -0.06
     Hammer
    -0.06
    igs
    -0.06
    Gay
    -0.06
    .Time
    -0.06
    POSITIVE LOGITS
    şam
    0.08
    MFLOAT
    0.07
     liệt
    0.07
     eyeb
    0.07
     pleasantly
    0.06
    ":"",↵
    0.06
     допомаг
    0.06
     підстав
    0.06
    (bp
    0.06
     شکست
    0.06
    Act Density 0.020%

    No Known Activations