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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    myModalLabel
    -0.07
    href
    -0.07
    olin
    -0.07
     воз
    -0.07
    Https
    -0.07
    誌
    -0.07
     <|
    -0.07
    FI
    -0.06
     solids
    -0.06
    itizen
    -0.06
    POSITIVE LOGITS
     が
    0.06
    anggan
    0.06
     acne
    0.06
     bypass
    0.06
     अच
    0.06
    _generic
    0.06
    (sprite
    0.06
    َج
    0.05
    h
    0.05
    watch
    0.05
    Act Density 0.011%

    No Known Activations