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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash

    scenes involving inappropriate or suggestive interactions between characters.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hills
    -0.07
     //////////////////////////////////////////////////////////////////////////
    -0.07
     Install
    -0.07
    _WINDOW
    -0.06
     lambda
    -0.06
     країни
    -0.06
    uct
    -0.06
     Below
    -0.06
    uet
    -0.06
    Interaction
    -0.06
    POSITIVE LOGITS
    赞
    0.08
    criminal
    0.07
     baj
    0.07
     Kaf
    0.07
     ті
    0.07
     tasarım
    0.07
    InstanceOf
    0.06
    virt
    0.06
    canf
    0.06
    CASCADE
    0.06
    Act Density 0.031%

    No Known Activations