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

    Neuronpedia

    INDEX
    Explanations

    , In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _softmax
    -0.07
     Zu
    -0.07
     Xi
    -0.07
    zap
    -0.07
     Tear
    -0.07
     socioeconomic
    -0.06
    Young
    -0.06
    晁
    -0.06
    Joe
    -0.06
    će
    -0.06
    POSITIVE LOGITS
    琈
    0.08
    בור
    0.07
    -bold
    0.07
    _MODULE
    0.07
    .getInputStream
    0.07
    תנוע
    0.07
     Verfügung
    0.07
     handmade
    0.07
     HDMI
    0.06
    ores
    0.06
    Act Density 0.020%

    No Known Activations