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

    Neuronpedia

    INDEX
    Explanations

    writing examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    作为
    -0.06
    らの
    -0.06
     станд
    -0.06
    'l
    -0.06
     FP
    -0.06
    ’daki
    -0.06
    >);↵
    -0.06
    成立
    -0.06
    кий
    -0.06
     additionally
    -0.06
    POSITIVE LOGITS
    sms
    0.06
    Ord
    0.06
    (steps
    0.06
     تصمیم
    0.06
    iking
    0.06
     jub
    0.06
    inition
    0.06
    gars
    0.06
    ryfall
    0.06
    humidity
    0.06
    Act Density 0.044%

    No Known Activations