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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash

    This neuron detects words describing cancellation or neutralization of impulses or forces.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    了解
    -0.06
    "'↵
    -0.06
     ICMP
    -0.06
     personals
    -0.06
     текст
    -0.06
     litres
    -0.06
     births
    -0.06
     nevy
    -0.06
    ados
    -0.06
     pistols
    -0.06
    POSITIVE LOGITS
    .ll
    0.07
    trimmed
    0.07
     SOCIAL
    0.07
    Called
    0.06
     Committee
    0.06
     FileManager
    0.06
    ModelState
    0.06
    atıcı
    0.06
    .С
    0.06
    .sy
    0.06
    Act Density 0.007%

    No Known Activations