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

    Neuronpedia

    INDEX
    Explanations

    code or ASCII

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隙
    -0.07
     Finder
    -0.07
    เอส
    -0.07
     peaks
    -0.06
    奶
    -0.06
    倏
    -0.06
     Fail
    -0.06
    个国家
    -0.06
    _malloc
    -0.06
    specifier
    -0.06
    POSITIVE LOGITS
    IVERY
    0.07
    brid
    0.06
    𬣞
    0.06
    民事
    0.06
     מאחורי
    0.06
    Directed
    0.06
    conditional
    0.06
     apartment
    0.06
     приятн
    0.06
    季
    0.06
    Act Density 0.031%

    No Known Activations