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

    Neuronpedia

    INDEX
    Explanations

    Mal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atrix
    -0.07
     spherical
    -0.07
     sscanf
    -0.06
    들이
    -0.06
    رده
    -0.06
    FINITE
    -0.06
     egreg
    -0.06
     successor
    -0.06
    240
    -0.06
    -unit
    -0.06
    POSITIVE LOGITS
     Mal
    0.10
     mal
    0.08
    Mal
    0.08
     小
    0.08
     Malk
    0.08
     technology
    0.07
     Malone
    0.07
     MAL
    0.07
    小
    0.07
    Months
    0.07
    Act Density 0.013%

    No Known Activations