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

    Neuronpedia

    INDEX
    Explanations

    undermining or disrupting plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordered
    0.39
     vacancy
    0.38
    &&(
    0.38
     Hormone
    0.36
    }]$
    0.36
     dairy
    0.35
     vá
    0.35
     hemisphere
    0.35
    ço
    0.35
    apy
    0.35
    POSITIVE LOGITS
     Показа
    0.43
    Targets
    0.41
    잠
    0.41
    toLowerCase
    0.40
    颤
    0.39
     排
    0.39
    ложения
    0.39
    Uploaded
    0.39
    potentially
    0.39
    getTarget
    0.38
    Act Density 0.000%

    No Known Activations