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

    Neuronpedia

    INDEX
    Explanations

    sum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     உட
    -0.08
    にも
    -0.08
     tubuh
    -0.08
    身体
    -0.08
     physiology
    -0.07
     ATS
    -0.07
     LMS
    -0.07
     теле
    -0.07
     physiological
    -0.07
     lifestyle
    -0.07
    POSITIVE LOGITS
     pře
    0.08
    (($
    0.08
    々
    0.08
    (((
    0.08
    ((((
    0.08
     (((
    0.08
     dû
    0.08
    Assoc
    0.08
    ((
    0.08
     {[
    0.08
    Act Density 0.029%

    No Known Activations