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

    Neuronpedia

    INDEX
    Explanations

    Studies and reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.06
    ाधन
    -0.06
    Layer
    -0.06
     Вик
    -0.06
    Handler
    -0.05
    olis
    -0.05
     revital
    -0.05
    มหานคร
    -0.05
     보호
    -0.05
    입니다
    -0.05
    POSITIVE LOGITS
     CGI
    0.07
     Hitch
    0.07
     szcz
    0.07
    .pat
    0.07
    /dir
    0.06
    (Target
    0.06
     dignity
    0.06
    .Framework
    0.06
     Deleting
    0.06
    _AL
    0.06
    Act Density 0.140%

    No Known Activations