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

    Neuronpedia

    INDEX
    Explanations

    enable, enabled, enabling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emphasis
    0.53
     Encyclopædia
    0.49
    odu
    0.49
    CT
    0.48
    ih
    0.47
    incomplete
    0.47
    em
    0.47
    ロウ
    0.47
    ensitive
    0.47
    COMPLETE
    0.46
    POSITIVE LOGITS
     habilit
    0.64
     Disable
    0.63
     Enable
    0.59
     disable
    0.58
     Enabling
    0.55
     enablement
    0.55
    Disable
    0.54
     disabled
    0.54
    disable
    0.54
     enabling
    0.53
    Act Density 0.008%

    No Known Activations