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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shift
    -0.07
    icopt
    -0.06
     Carb
    -0.06
     Pride
    -0.06
     april
    -0.06
    Loss
    -0.06
    accept
    -0.06
     Shift
    -0.06
     distrib
    -0.06
    들도
    -0.06
    POSITIVE LOGITS
    辰
    0.07
    ミュ
    0.07
    _ctrl
    0.06
     mezun
    0.06
    Qué
    0.06
     гри
    0.06
    wers
    0.06
    ैक
    0.06
     Skinner
    0.06
     hormonal
    0.06
    Act Density 0.000%

    No Known Activations