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

    Neuronpedia

    INDEX
    Explanations

    Incomplete text snippets

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the phrase “pick up,” as in “pick up lines.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Com
    -0.07
    وپ
    -0.07
     outset
    -0.07
    Hur
    -0.07
    -side
    -0.07
     Huck
    -0.06
    _Def
    -0.06
     Inter
    -0.06
     Nick
    -0.06
    beta
    -0.06
    POSITIVE LOGITS
     ${(
    0.07
    (library
    0.06
    ----------</
    0.06
    observeOn
    0.06
     erreur
    0.06
    //}↵
    0.06
    nila
    0.06
     ذه
    0.06
    .tools
    0.06
    .INVISIBLE
    0.06
    Act Density 0.016%

    No Known Activations