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

    Neuronpedia

    INDEX
    Explanations

    describing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рович
    -0.07
    되
    -0.07
    Ear
    -0.07
    Monday
    -0.07
    Attack
    -0.07
     stuck
    -0.07
     lin
    -0.06
    .quote
    -0.06
     Qt
    -0.06
     choking
    -0.06
    POSITIVE LOGITS
    'LBL
    0.07
    _SF
    0.06
     SF
    0.06
    월까지
    0.06
    (od
    0.06
    ALLENG
    0.06
     angered
    0.06
    mapped
    0.06
    /status
    0.06
    _interp
    0.06
    Act Density 0.095%

    No Known Activations