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

    Neuronpedia

    INDEX
    Explanations

    genetics and inheritance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
     indiscrim
    -0.07
    在那里
    -0.07
    .Reader
    -0.07
     אותם
    -0.07
     للغا
    -0.06
    Forever
    -0.06
     Catholic
    -0.06
    .setImage
    -0.06
     ()↵
    -0.06
    POSITIVE LOGITS
    룍
    0.07
     Trust
    0.07
    SO
    0.07
     PAL
    0.07
    Rates
    0.07
    数
    0.07
    $ar
    0.06
     Fix
    0.06
     Kubernetes
    0.06
    AX
    0.06
    Act Density 0.009%

    No Known Activations