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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ▼
    -0.07
     '".$_
    -0.07
    902
    -0.07
    �
    -0.07
     张
    -0.06
     работать
    -0.06
    ='".$_
    -0.06
    #aa
    -0.06
     ав
    -0.06
    であ
    -0.06
    POSITIVE LOGITS
     updated
    0.06
    GORITHM
    0.06
    _extensions
    0.06
     rates
    0.06
    概
    0.06
    _disk
    0.06
     Observation
    0.06
     vines
    0.06
    action
    0.06
     Loose
    0.06
    Act Density 0.000%

    No Known Activations