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

    Neuronpedia

    INDEX
    Explanations

    Chemistry fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tunis
    -0.08
     Working
    -0.07
     congen
    -0.07
     Ten
    -0.07
     Brighton
    -0.07
     hott
    -0.07
    .vehicle
    -0.07
    בני
    -0.06
     Bik
    -0.06
    绅
    -0.06
    POSITIVE LOGITS
    亲近
    0.07
    如此
    0.07
    交代
    0.07
    _RS
    0.07
    مسجد
    0.07
     נגד
    0.07
    讲解
    0.07
     mie
    0.06
    聞く
    0.06
    .AddRange
    0.06
    Act Density 0.028%

    No Known Activations