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

    Neuronpedia

    INDEX
    Explanations

    choices and reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FILES
    -0.08
    保证
    -0.08
    验
    -0.08
     infe
    -0.08
     Schutz
    -0.08
    鹏
    -0.08
     enje
    -0.08
     treba
    -0.08
     deveriam
    -0.08
     uiteraard
    -0.07
    POSITIVE LOGITS
     impulses
    0.09
     Augustine
    0.09
     calmly
    0.09
     jot
    0.09
     спокойно
    0.09
     habitual
    0.08
     Twitch
    0.08
    Impulse
    0.08
     Ayur
    0.08
    Immediate
    0.08
    Act Density 0.020%

    No Known Activations