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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iem
    -0.07
    _tickets
    -0.07
    bars
    -0.07
    Hex
    -0.07
     is
    -0.07
     strikes
    -0.06
     SCR
    -0.06
    фор
    -0.06
    ']=='
    -0.06
    RequestBody
    -0.06
    POSITIVE LOGITS
    03
    0.06
    想要
    0.06
    _aligned
    0.06
     trusted
    0.06
     Č
    0.06
     오늘
    0.06
    gili
    0.06
    elleicht
    0.06
     ULONG
    0.05
     какой
    0.05
    Act Density 0.241%

    No Known Activations