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

    Neuronpedia

    INDEX
    Explanations

    stories and novels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beneficiaries
    -0.09
     fermented
    -0.09
     haut
    -0.09
     individuos
    -0.09
     vajalik
    -0.08
     hipert
    -0.08
     selten
    -0.08
    Individuals
    -0.08
     prolifer
    -0.08
    顶部
    -0.08
    POSITIVE LOGITS
     girl
    0.08
     Kal
    0.07
     clans
    0.07
    ♡
    0.07
     princess
    0.07
    step
    0.07
     लड़की
    0.07
    忍
    0.07
     forgiving
    0.07
     DPS
    0.07
    Act Density 0.003%

    No Known Activations