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

    Neuronpedia

    INDEX
    Explanations

    otypes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CALC
    -0.07
     corrected
    -0.06
     dong
    -0.06
    .Ma
    -0.06
     literal
    -0.06
    oriented
    -0.06
    dım
    -0.06
     ma
    -0.06
    airport
    -0.06
     rebate
    -0.06
    POSITIVE LOGITS
     hip
    0.07
     assessing
    0.07
    že
    0.07
     smaller
    0.07
     Нав
    0.06
    ниц
    0.06
    メント
    0.06
     tutorial
    0.06
    (Map
    0.06
    φαρ
    0.06
    Act Density 0.000%

    No Known Activations