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

    Neuronpedia

    INDEX
    Explanations

    timestamps and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     види
    0.40
    Touch
    0.39
    怖い
    0.38
     प
    0.38
     VIDE
    0.37
     हिटलर
    0.37
    ི་
    0.37
    ArgsEnv
    0.36
    CXX
    0.36
    щины
    0.36
    POSITIVE LOGITS
     meteen
    0.39
     immediately
    0.36
    ทัน
    0.35
    opr
    0.35
     instantly
    0.33
     hemen
    0.32
     immediatamente
    0.32
    mless
    0.32
    elb
    0.32
    anya
    0.31
    Act Density 0.005%

    No Known Activations