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

    Neuronpedia

    INDEX
    Explanations

    (e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cré
    -0.07
     кру
    -0.07
    aday
    -0.07
    adjust
    -0.06
     권
    -0.06
     ogłoszeni
    -0.06
    toList
    -0.06
    -debug
    -0.06
     Sender
    -0.06
    كي
    -0.06
    POSITIVE LOGITS
     nons
    0.08
     Scenes
    0.07
     Another
    0.07
    年限
    0.07
    \F
    0.07
     hc
    0.07
     cues
    0.07
     opportunities
    0.07
    𬊤
    0.06
     filePath
    0.06
    Act Density 0.001%

    No Known Activations