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
     Peygamber
    -0.07
     heavily
    -0.07
    (controller
    -0.07
    .xyz
    -0.07
     formulated
    -0.06
    зем
    -0.06
    Pg
    -0.06
     Executive
    -0.06
    ?,?,
    -0.06
    REDIENT
    -0.06
    POSITIVE LOGITS
    ื่
    0.07
    ournals
    0.06
     spices
    0.06
    賽
    0.06
    	query
    0.06
    iday
    0.06
     WoW
    0.06
     soudu
    0.06
    :len
    0.06
    ılığıyla
    0.06
    Act Density 0.040%

    No Known Activations