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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -toggle
    -0.09
    Activated
    -0.07
    ࡑ
    -0.07
    especially
    -0.07
     spiele
    -0.07
    -----------↵↵
    -0.07
    orn
    -0.07
    截止
    -0.07
    "So
    -0.07
    ển
    -0.06
    POSITIVE LOGITS
     nau
    0.07
     hats
    0.07
    _tensor
    0.07
     الأمريكية
    0.07
     communauté
    0.07
    _abort
    0.06
    _UNUSED
    0.06
     داخل
    0.06
    見て
    0.06
    עית
    0.06
    Act Density 0.010%

    No Known Activations