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

    Neuronpedia

    INDEX
    Explanations

    www

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eh
    -0.08
    bc
    -0.07
    صفقة
    -0.07
    .vertex
    -0.07
    TexCoord
    -0.07
    codile
    -0.07
     aes
    -0.07
    谨慎
    -0.07
    e
    -0.07
    rus
    -0.07
    POSITIVE LOGITS
    _FAMILY
    0.08
     /^[
    0.07
    utility
    0.07
    -desktop
    0.07
    מרכ
    0.06
     intimidation
    0.06
    *>::
    0.06
    Framework
    0.06
     '">
    0.06
    .Experimental
    0.06
    Act Density 0.004%

    No Known Activations