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

    Neuronpedia

    INDEX
    Explanations

    general English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squat
    -0.07
     Nel
    -0.06
     الرو
    -0.06
     Παρα
    -0.06
    :ss
    -0.06
    	conn
    -0.06
     Letters
    -0.06
    limits
    -0.06
     reigning
    -0.06
     Secrets
    -0.06
    POSITIVE LOGITS
    -mode
    0.07
     haya
    0.07
    FUL
    0.07
    سد
    0.06
    prite
    0.06
    .DropTable
    0.06
     unsuccessful
    0.06
     bunker
    0.06
    PROFILE
    0.06
     Moody
    0.06
    Act Density 0.000%

    No Known Activations