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

    Neuronpedia

    INDEX
    Explanations

    acid

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “acid.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .EditValue
    -0.07
    投资
    -0.06
    ceil
    -0.06
    альному
    -0.06
    -ret
    -0.06
    idata
    -0.06
    *
↵
    -0.06
    Stmt
    -0.06
    -method
    -0.06
    lick
    -0.06
    POSITIVE LOGITS
    详情
    0.07
     풀
    0.07
     TOR
    0.06
     фор
    0.06
    خصص
    0.06
    REGION
    0.06
    .of
    0.06
    .slice
    0.06
     �
    0.06
    атегор
    0.06
    Act Density 0.003%

    No Known Activations