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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pick
    -0.07
    PROTO
    -0.06
     Fro
    -0.06
     CT
    -0.06
    Grant
    -0.06
    <Contact
    -0.06
    .Interval
    -0.06
    Hor
    -0.06
     FIR
    -0.06
     Hast
    -0.06
    POSITIVE LOGITS
     behave
    0.07
     prostituerade
    0.07
     velké
    0.06
    elu
    0.06
     uphe
    0.06
    -↵
    0.06
    (py
    0.06
     comma
    0.06
     göre
    0.06
     그가
    0.06
    Act Density 0.046%

    No Known Activations