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

    Neuronpedia

    INDEX
    Explanations

    mine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tob
    -0.08
     Stap
    -0.07
    Speaking
    -0.07
    .Observable
    -0.07
    花开
    -0.07
     confess
    -0.07
    ocrates
    -0.07
     diary
    -0.07
    נוס
    -0.07
    (itr
    -0.07
    POSITIVE LOGITS
    并与
    0.08
    沉重
    0.07
    زمة
    0.07
     mines
    0.07
    .ingredients
    0.07
     نقاط
    0.07
    .xml
    0.07
     ning
    0.07
    око
    0.07
    amine
    0.06
    Act Density 0.010%

    No Known Activations