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
    Bre
    -0.07
     April
    -0.07
     ה
    -0.06
    “No
    -0.06
     Why
    -0.06
    Why
    -0.06
     Cottage
    -0.06
    warning
    -0.06
    	Delete
    -0.06
     Biological
    -0.06
    POSITIVE LOGITS
    perienced
    0.07
     migrating
    0.06
     ragaz
    0.06
     Spectrum
    0.06
     Mek
    0.06
    .RemoveEmptyEntries
    0.06
     �
    0.06
    重複
    0.06
     Kanun
    0.06
    ﾞ
    0.06
    Act Density 0.000%

    No Known Activations