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

    Neuronpedia

    INDEX
    Explanations

    command line/installation instructions

    np_max-act · gemini-2.0-flash

    This neuron detects shell command sequences (e.g. “cd … && rm … && wget …”) in bash scripts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EFI
    -0.07
    Makes
    -0.07
    âk
    -0.06
    znik
    -0.06
     είχαν
    -0.06
     themselves
    -0.06
     Lucy
    -0.06
    Vict
    -0.06
    門
    -0.06
     yourself
    -0.06
    POSITIVE LOGITS
     WAIT
    0.07
     subpoena
    0.06
     同
    0.06
    .HeaderText
    0.06
    axes
    0.06
    ）。
    0.06
    .divide
    0.06
     จำก
    0.06
     pubb
    0.06
    dat
    0.05
    Act Density 0.009%

    No Known Activations