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

    Neuronpedia

    INDEX
    Explanations

    shown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BAD
    -0.07
     otherwise
    -0.06
    姉
    -0.06
     intValue
    -0.06
    ωμα
    -0.06
     编
    -0.06
    prod
    -0.06
    โปรแกรม
    -0.06
    Repair
    -0.06
     Аб
    -0.06
    POSITIVE LOGITS
    bl
    0.07
     luego
    0.06
    ечно
    0.06
     maintaining
    0.06
    -k
    0.06
    .");
↵
    0.06
     Pending
    0.06
    僅
    0.06
    (Collision
    0.05
     meziná
    0.05
    Act Density 0.021%

    No Known Activations