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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    org
    -0.07
    ,arr
    -0.07
    宾客
    -0.07
     indeed
    -0.07
    ERNEL
    -0.07
     לחלוטין
    -0.06
     neh
    -0.06
     vocalist
    -0.06
     tossed
    -0.06
    出てくる
    -0.06
    POSITIVE LOGITS
    rection
    0.08
    Errors
    0.08
     eighth
    0.07
    heure
    0.07
    _diff
    0.07
    editing
    0.07
    放映
    0.07
     urban
    0.07
    phy
    0.07
     partes
    0.06
    Act Density 0.190%

    No Known Activations