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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heck
    -0.07
    ・・
    -0.07
     Gill
    -0.06
    -0.06
     statistics
    -0.06
    ODO
    -0.06
    (stock
    -0.06
     recipient
    -0.06
     Matt
    -0.06
    asso
    -0.06
    POSITIVE LOGITS
    <input
    0.10
     interes
    0.07
    .entry
    0.07
     outcry
    0.07
     立
    0.07
    Inline
    0.07
     phát
    0.06
     erotisch
    0.06
     incoming
    0.06
    출장샵
    0.06
    Act Density 0.003%

    No Known Activations