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

    Neuronpedia

    INDEX
    Explanations

    display or hide UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ABASE
    0.42
    מח
    0.40
    モーション
    0.39
    🔄
    0.37
    FORMANCE
    0.37
    CHUNK
    0.37
    chsler
    0.36
    爌
    0.36
     vertebrates
    0.35
    Ŋ
    0.35
    POSITIVE LOGITS
     hidden
    0.96
    hidden
    0.92
     Hidden
    0.86
     hide
    0.85
    Hidden
    0.85
     hiding
    0.84
    setVisible
    0.83
    隐藏
    0.83
     Hide
    0.82
    hide
    0.81
    Act Density 0.074%

    No Known Activations