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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spawned
    -0.08
     ammunition
    -0.08
     Insurance
    -0.07
    arma
    -0.07
     thôi
    -0.07
     Magic
    -0.07
    ovie
    -0.07
    ollywood
    -0.07
    eah
    -0.07
    𬳶
    -0.07
    POSITIVE LOGITS
     lb
    0.07
     visitors
    0.07
    $r
    0.07
    (act
    0.07
    訪れ
    0.07
    𝑆
    0.06
     vis
    0.06
     зр
    0.06
     polarity
    0.06
     angles
    0.06
    Act Density 0.071%

    No Known Activations