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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '_
    -0.07
    覺
    -0.07
    'I
    -0.06
     níž
    -0.06
    .lesson
    -0.06
    .social
    -0.06
    .Test
    -0.06
     nhất
    -0.06
    ียนบ
    -0.06
    PROP
    -0.06
    POSITIVE LOGITS
     philosoph
    0.07
    rador
    0.07
     GAR
    0.06
     revised
    0.06
    Samsung
    0.06
     Capac
    0.06
     Asi
    0.06
     Cannon
    0.06
    ALIGN
    0.06
     кар
    0.06
    Act Density 0.034%

    No Known Activations