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

    Neuronpedia

    INDEX
    Explanations

    teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     designated
    -0.07
    状態
    -0.07
    业
    -0.07
     Этот
    -0.07
     �
    -0.06
     heatmap
    -0.06
    _on
    -0.06
    手を
    -0.06
    低
    -0.06
     дан
    -0.06
    POSITIVE LOGITS
    IntoConstraints
    0.08
    SearchParams
    0.07
    .COM
    0.07
     negoci
    0.07
    ½
    0.07
    ICLE
    0.07
    -stats
    0.07
    .now
    0.07
    .NotNil
    0.06
     Proposition
    0.06
    Act Density 0.161%

    No Known Activations