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

    Neuronpedia

    INDEX
    Explanations

    temper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     감사
    -0.07
     音
    -0.06
     Skin
    -0.06
    75
    -0.06
     dàng
    -0.06
     Eston
    -0.06
    ahl
    -0.06
    ीएस
    -0.06
    567
    -0.06
    PERTY
    -0.06
    POSITIVE LOGITS
     enraged
    0.08
     mob
    0.07
    =time
    0.07
     infuri
    0.07
     underside
    0.06
     credit
    0.06
     enacted
    0.06
     NSRange
    0.06
    *↵↵
    0.06
    quired
    0.06
    Act Density 0.021%

    No Known Activations