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

    Neuronpedia

    INDEX
    Explanations

    Null values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Safety
    -0.08
    (my
    -0.07
     концеп
    -0.07
     Yak
    -0.06
     safety
    -0.06
     doctors
    -0.06
    .Redis
    -0.06
    (q
    -0.06
     fades
    -0.06
     nostalg
    -0.06
    POSITIVE LOGITS
     изготов
    0.06
     wxT
    0.06
    加载
    0.06
     मतलब
    0.06
     Vapor
    0.06
    ULER
    0.06
    υτό
    0.06
     MCC
    0.06
     breakpoints
    0.06
     -*-
    0.06
    Act Density 0.020%

    No Known Activations