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

    Neuronpedia

    INDEX
    Explanations

    Moz

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >)
    -0.06
    ,$
    -0.06
     Destroy
    -0.06
    OrDefault
    -0.06
     استاندارد
    -0.06
     blatantly
    -0.06
     Floating
    -0.06
    "|
    -0.06
    ประก
    -0.06
     -->↵↵↵
    -0.06
    POSITIVE LOGITS
    مد
    0.07
     Op
    0.07
    .ng
    0.07
     смеш
    0.06
     entert
    0.06
    caps
    0.06
    主任
    0.06
    念
    0.06
     او
    0.06
     celui
    0.06
    Act Density 0.001%

    No Known Activations