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

    Neuronpedia

    INDEX
    Explanations

    Paul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    volt
    -0.30
    -Jul
    -0.29
    èĢĥèĻijåĪ°
    -0.26
    庸
    -0.26
     flutter
    -0.26
    -stats
    -0.26
     Formats
    -0.25
    妩
    -0.25
    ngen
    -0.25
    itarian
    -0.25
    POSITIVE LOGITS
    èĭ¦
    0.29
    cd
    0.29
     cd
    0.27
    Ì
    0.27
    l
    0.27
    ri
    0.26
    ld
    0.26
    ver
    0.26
     increasing
    0.26
    rio
    0.25
    Act Density 0.212%

    No Known Activations