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

    Neuronpedia

    INDEX
    Explanations

    Let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    logical
    -0.07
    ‫
    -0.07
     ولك
    -0.06
     Blanc
    -0.06
    shows
    -0.06
    ℃
    -0.06
    helm
    -0.06
    valid
    -0.06
     malls
    -0.06
     Featuring
    -0.06
    POSITIVE LOGITS
     clit
    0.06
     btw
    0.06
     temptation
    0.06
    /mit
    0.06
     instances
    0.05
     linebacker
    0.05
    LOAT
    0.05
    ertificate
    0.05
    _term
    0.05
     firearms
    0.05
    Act Density 0.008%

    No Known Activations