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

    Neuronpedia

    INDEX
    Explanations

    perforation

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “perforation” (and its variants like “perforated”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _trees
    -0.07
    (State
    -0.07
     Cy
    -0.06
    (ps
    -0.06
    Banner
    -0.06
    ,current
    -0.06
    _policy
    -0.06
    (play
    -0.06
    -under
    -0.06
     NEWS
    -0.06
    POSITIVE LOGITS
     perfor
    0.13
     Encrypt
    0.07
     Angelo
    0.07
     Comet
    0.07
     "'
    0.07
     못
    0.07
    εργ
    0.07
     fencing
    0.07
    ’.
    0.07
     finishing
    0.07
    Act Density 0.002%

    No Known Activations