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

    Neuronpedia

    INDEX
    Explanations

    call, stock, forgotten lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    หลาย
    0.50
     portraying
    0.49
     więks
    0.49
     CCI
    0.48
     scheda
    0.48
     prédio
    0.47
     flere
    0.46
     MCSF
    0.46
     settim
    0.45
     koszt
    0.45
    POSITIVE LOGITS
    Forgot
    0.42
    ol
    0.42
    Shift
    0.41
    oges
    0.40
    all
    0.39
    ush
    0.39
    OnChange
    0.39
    ax
    0.38
    way
    0.37
    paren
    0.37
    Act Density 0.004%

    No Known Activations