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

    Neuronpedia

    INDEX
    Explanations

    urges and mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Socialista
    0.46
    صیٰ
    0.43
     disusun
    0.43
    غانستان
    0.42
     बीएससी
    0.42
     ಕರ್ನಾಟಕ
    0.42
     Kyushu
    0.41
     کمپیوٹر
    0.41
     Latvij
    0.41
     столб
    0.41
    POSITIVE LOGITS
    选择
    0.38
    Ic
    0.38
    izza
    0.38
    OT
    0.37
     posti
    0.35
    ật
    0.35
    ange
    0.35
    Type
    0.35
     актива
    0.34
     lodge
    0.34
    Act Density 0.131%

    No Known Activations