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

    Neuronpedia

    INDEX
    Explanations

    testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —for
    -0.07
     iz
    -0.06
    .gs
    -0.06
     قال
    -0.06
    IDER
    -0.06
     mega
    -0.06
     forg
    -0.06
    egis
    -0.06
    सन
    -0.06
     Plato
    -0.06
    POSITIVE LOGITS
    �
    0.07
     premiere
    0.06
     exemptions
    0.06
    EncodingException
    0.06
     pleasantly
    0.06
    (alpha
    0.06
     $('<
    0.06
    三级
    0.06
    ;


↵
    0.06
    .convert
    0.06
    Act Density 0.007%

    No Known Activations