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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RatingBar
    -0.46
     EClass
    -0.46
    вайтесь
    -0.46
     simplifié
    -0.44
     Gira
    -0.44
    zuführen
    -0.44
     calendriers
    -0.43
     aidant
    -0.43
    jena
    -0.42
     Rust
    -0.42
    POSITIVE LOGITS
    BeginContext
    0.70
     ***!
    0.63
     مشين
    0.63
    Попис
    0.63
    GOTREF
    0.62
     تضيفلها
    0.60
    ConstraintMaker
    0.60
    andExpect
    0.59
    __*/
    0.59
     betweenstory
    0.59
    Act Density 0.000%

    No Known Activations