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

    Neuronpedia

    INDEX
    Explanations

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edes
    -0.08
     डिज
    -0.08
     desain
    -0.07
     पर्य
    -0.07
     despertar
    -0.07
    _FE
    -0.07
    cur
    -0.07
     Dis
    -0.07
    imum
    -0.07
     절
    -0.07
    POSITIVE LOGITS
     wording
    0.09
     самого
    0.08
     যেন
    0.08
    ’expression
    0.08
    үүний
    0.08
    Regarding
    0.08
     phrase
    0.08
     തന്നെ
    0.08
     phr
    0.08
     strán
    0.07
    Act Density 0.008%

    No Known Activations