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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шир
    -0.07
    chat
    -0.06
    یط
    -0.06
    ("")
    -0.06
    ergus
    -0.06
    _likelihood
    -0.06
     š
    -0.06
     diğer
    -0.06
     resolver
    -0.06
    .favorite
    -0.06
    POSITIVE LOGITS
    大学
    0.07
    (resourceName
    0.06
     inverse
    0.06
    roleum
    0.06
     Gaines
    0.06
     calling
    0.06
    φο
    0.06
     CD
    0.06
    uint
    0.06
    .external
    0.06
    Act Density 0.009%

    No Known Activations