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

    Neuronpedia

    INDEX
    Explanations

    MVC framework

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     these
    -0.07
    Birthday
    -0.07
     nearer
    -0.07
     еще
    -0.06
     Races
    -0.06
     locked
    -0.06
    .createElement
    -0.06
    .element
    -0.06
     Subtract
    -0.06
     These
    -0.06
    POSITIVE LOGITS
    รณ
    0.07
    GRES
    0.07
     lul
    0.06
    onnement
    0.06
     PRES
    0.06
    fic
    0.06
    にお
    0.06
    fef
    0.06
     renters
    0.06
    �
    0.05
    Act Density 0.033%

    No Known Activations