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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نزل
    -0.08
     characterize
    -0.07
     건
    -0.07
     vertex
    -0.07
     patron
    -0.07
     cross
    -0.07
     mortal
    -0.07
    传
    -0.07
    umm
    -0.06
     validate
    -0.06
    POSITIVE LOGITS
     Phú
    0.08
    weeks
    0.07
    鳤
    0.07
    合作协议
    0.07
    ألو
    0.07
    学前
    0.07
    ABCDEFG
    0.07
    charges
    0.07
    cheiden
    0.07
    ESTAMP
    0.07
    Act Density 0.000%

    No Known Activations