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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기간
    -0.09
     Madness
    -0.08
     eros
    -0.08
     مناطق
    -0.07
     anledning
    -0.07
     rendimento
    -0.07
     modalidade
    -0.07
    "ג
    -0.07
     Moda
    -0.07
     etabler
    -0.07
    POSITIVE LOGITS
     recently
    0.10
     fiercely
    0.09
     unaware
    0.09
     fierce
    0.09
     reluctant
    0.09
     Recently
    0.09
     penchant
    0.08
    Recently
    0.08
     lately
    0.08
     believes
    0.08
    Act Density 0.031%

    No Known Activations