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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    callbacks
    -0.07
    datal
    -0.07
    diği
    -0.06
    -reported
    -0.06
     SHARES
    -0.06
     substituted
    -0.06
    .Actions
    -0.06
    iz
    -0.06
    Materials
    -0.06
    Beginning
    -0.06
    POSITIVE LOGITS
     quaint
    0.07
    	initialize
    0.06
     DOMAIN
    0.06
     एन
    0.06
     curr
    0.06
     �
    0.06
    (listener
    0.06
    强
    0.06
    obili
    0.06
    airo
    0.06
    Act Density 0.015%

    No Known Activations