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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pel
    -0.07
    Greg
    -0.07
    Roger
    -0.07
    Experts
    -0.06
    Viet
    -0.06
    'app
    -0.06
     planets
    -0.06
    くれた
    -0.06
     qc
    -0.06
     Walter
    -0.06
    POSITIVE LOGITS
     Hentai
    0.06
     anatomy
    0.06
     libero
    0.06
     Notebook
    0.06
     IM
    0.06
    _REFERER
    0.06
    kinson
    0.06
    (vars
    0.05
     Rc
    0.05
     graphql
    0.05
    Act Density 0.000%

    No Known Activations