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

    Neuronpedia

    INDEX
    Explanations

    SOFTWARE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    今后
    -0.07
     Dean
    -0.07
    خام
    -0.07
    rolled
    -0.07
     manage
    -0.07
    rieve
    -0.07
    놉
    -0.06
     Occupy
    -0.06
    ).'</
    -0.06
     fill
    -0.06
    POSITIVE LOGITS
     fortress
    0.08
    奘
    0.07
     Laz
    0.07
    methodName
    0.07
    FormatException
    0.07
    彩虹
    0.07
     위해서
    0.07
     וד
    0.07
    __;
    0.07
    normal
    0.06
    Act Density 0.003%

    No Known Activations