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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frank
    -0.07
    rts
    -0.07
    ぬ
    -0.06
     inspires
    -0.06
    lu
    -0.06
     tertiary
    -0.06
    ník
    -0.06
    extras
    -0.06
    �
    -0.06
    arrow
    -0.06
    POSITIVE LOGITS
    \P
    0.07
    !“
    0.07
     万円
    0.06
    istency
    0.06
    戒
    0.06
     Tales
    0.06
     siyaset
    0.06
     countered
    0.06
    _Control
    0.06
     pár
    0.06
    Act Density 0.025%

    No Known Activations