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

    Neuronpedia

    INDEX
    Explanations

    controls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᅠ
    -0.07
     {}
    -0.07
    コピー
    -0.07
    illy
    -0.07
    ')}>↵
    -0.06
     MPG
    -0.06
    (),
↵
    -0.06
    ℋ
    -0.06
     orb
    -0.06
    Express
    -0.06
    POSITIVE LOGITS
     узна
    0.08
     ويمكن
    0.07
    _MENU
    0.07
     JNIEnv
    0.07
    _stream
    0.07
    (models
    0.07
    _pe
    0.07
    .currentState
    0.07
    (download
    0.07
    -even
    0.07
    Act Density 0.026%

    No Known Activations