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

    Neuronpedia

    INDEX
    Explanations

    dangerous and addictive drugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大胆
    1.25
    дача
    1.22
    ریٹر
    1.17
    慮
    1.16
     Renaud
    1.14
    DispatchRequest
    1.13
    ைத்
    1.12
     subordination
    1.10
    Detectable
    1.10
    掊
    1.09
    POSITIVE LOGITS
    o
    1.36
    or
    1.30
    am
    1.29
    od
    1.25
    री
    1.20
    en
    1.19
    r
    1.19
    ам
    1.18
    mins
    1.18
    orche
    1.14
    Act Density 0.000%

    No Known Activations