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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Battery
    -0.07
     테
    -0.07
     ($("#
    -0.07
    atasets
    -0.06
     lowers
    -0.06
     rules
    -0.06
     filles
    -0.06
    vailability
    -0.06
    angen
    -0.06
    lder
    -0.06
    POSITIVE LOGITS
    Suc
    0.07
     aute
    0.07
    ได
    0.07
    دو
    0.07
     وذلك
    0.07
     freshman
    0.06
    bí
    0.06
    produto
    0.06
     giàu
    0.06
    .csrf
    0.06
    Act Density 0.000%

    No Known Activations