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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toolStrip
    -0.06
    敌
    -0.06
    低
    -0.06
    번호
    -0.06
    ři
    -0.06
    .deserialize
    -0.06
    港
    -0.06
    _CONNECT
    -0.05
     заб
    -0.05
     MediaPlayer
    -0.05
    POSITIVE LOGITS
     compañ
    0.07
    ophys
    0.07
     बद
    0.07
     Waters
    0.07
    VISION
    0.07
     Or
    0.07
     Spells
    0.06
     kot
    0.06
    >V
    0.06
     cleaner
    0.06
    Act Density 0.025%

    No Known Activations