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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sl
    -0.07
    -car
    -0.07
     حسن
    -0.07
    ポ
    -0.06
     molding
    -0.06
    :w
    -0.06
     spol
    -0.06
     manpower
    -0.06
     TF
    -0.06
     Hospitality
    -0.06
    POSITIVE LOGITS
    opped
    0.07
    nodiscard
    0.06
    ))))
    0.06
     Damascus
    0.06
    .modelo
    0.06
     proceed
    0.06
    ाइड
    0.06
    uellen
    0.06
    	next
    0.06
     fica
    0.06
    Act Density 0.023%

    No Known Activations