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

    Neuronpedia

    INDEX
    Explanations

    hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.36
     jeopard
    1.18
    b
    1.18
     générateur
    1.15
    SH
    1.13
    i
    1.06
    },
    1.05
    জ
    0.98
    h
    0.98
     reorgan
    0.96
    POSITIVE LOGITS
    지
    1.34
    وں
    1.27
    ز
    1.21
    ai
    1.16
    وا
    1.13
    هم
    1.12
    ית
    1.12
    ام
    1.10
    ні
    1.08
     In
    1.07
    Act Density 0.001%

    No Known Activations