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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ukan
    -0.07
    EMPLARY
    -0.06
    ToLower
    -0.06
     ]);
    -0.06
    (factor
    -0.06
    .available
    -0.06
     "/");↵
    -0.06
    :)])
    -0.06
    YOU
    -0.06
    .MockMvc
    -0.06
    POSITIVE LOGITS
    ्बर
    0.07
    chied
    0.06
    /math
    0.06
    �
    0.06
    .DateTime
    0.06
     coraz
    0.06
     Федераль
    0.06
     beings
    0.06
     explosions
    0.06
    hiro
    0.06
    Act Density 0.003%

    No Known Activations