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

    Neuronpedia

    INDEX
    Explanations

    was informed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imension
    -0.07
    raid
    -0.06
     Cmd
    -0.06
    (candidate
    -0.06
     corresponds
    -0.06
    .Button
    -0.06
     regularly
    -0.06
    Course
    -0.06
    .Ignore
    -0.06
    Construct
    -0.06
    POSITIVE LOGITS
    ека
    0.07
     квад
    0.07
    咨询
    0.07
     programma
    0.07
    +↵↵
    0.06
     nécessaire
    0.06
     Trusted
    0.06
    ″
    0.06
    '],['
    0.06
    "],["
    0.06
    Act Density 0.084%

    No Known Activations