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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictionaries
    -0.06
     notebooks
    -0.06
     когда
    -0.06
     nếu
    -0.06
    ittest
    -0.06
     Dy
    -0.06
     údaj
    -0.06
     dư�
    -0.06
     بدن
    -0.06
    Hor
    -0.06
    POSITIVE LOGITS
     rake
    0.07
    -we
    0.07
    integration
    0.07
    /en
    0.07
    overlap
    0.07
    warm
    0.07
     виб
    0.07
    /sp
    0.07
     �
    0.07
    fsp
    0.07
    Act Density 0.007%

    No Known Activations