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

    Neuronpedia

    INDEX
    Explanations

    folding movement

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing folding or stowing actions or positions (e.g. “fold,” “folded,” “stowed,” “flat”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rus
    -0.08
     merciless
    -0.07
    notice
    -0.07
    Independent
    -0.07
    872
    -0.07
    ,
↵
    -0.07
    873
    -0.06
    402
    -0.06
    (){
↵
    -0.06
    くん
    -0.06
    POSITIVE LOGITS
     Schedule
    0.07
    .</
    0.07
    磁
    0.06
     unpaid
    0.06
     Veter
    0.06
     Voyage
    0.06
    SEP
    0.06
     Display
    0.06
    ató
    0.06
     embod
    0.06
    Act Density 0.010%

    No Known Activations