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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idon
    -0.07
     SHOW
    -0.07
    ucked
    -0.06
     CSL
    -0.06
     Surveillance
    -0.06
     Recreation
    -0.06
     didSelect
    -0.06
     Tib
    -0.06
    raz
    -0.06
     جهانی
    -0.06
    POSITIVE LOGITS
     glfw
    0.07
    ncmp
    0.06
    itung
    0.06
     greatness
    0.06
    िकत
    0.06
     dependencies
    0.06
    TextField
    0.06
     행
    0.06
    暴
    0.06
     csak
    0.06
    Act Density 0.013%

    No Known Activations