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

    Neuronpedia

    INDEX
    Explanations

    Programming help

    np_max-act · gemini-2.0-flash

    This neuron detects Python REPL/tool instruction tokens—i.e. places where the text is giving or invoking Python‐code commands.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    르는
    -0.06
     Converted
    -0.06
    optgroup
    -0.06
     oi
    -0.06
    (".");↵
    -0.06
    :]
    -0.06
     Lexington
    -0.06
     pregn
    -0.06
     derail
    -0.06
    IBAction
    -0.06
    POSITIVE LOGITS
     أمريكي
    0.07
     acclaim
    0.07
    __)
    0.06
     ejaculation
    0.06
     lei
    0.06
    .Sprite
    0.06
     legalized
    0.06
     tonight
    0.06
     maneuver
    0.06
     OnClickListener
    0.06
    Act Density 0.007%

    No Known Activations