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

    Neuronpedia

    INDEX
    Explanations

    instruct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iven
    -0.08
     malé
    -0.07
    láv
    -0.07
     праців
    -0.07
     сили
    -0.07
    _INTERNAL
    -0.06
    erial
    -0.06
    ospital
    -0.06
    공부
    -0.06
     verbs
    -0.06
    POSITIVE LOGITS
     KR
    0.07
    Boy
    0.06
    请
    0.06
    West
    0.06
     constexpr
    0.06
    Crime
    0.06
    Ok
    0.06
     Dod
    0.06
    Θ
    0.06
     dash
    0.06
    Act Density 0.000%

    No Known Activations