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

    Neuronpedia

    INDEX
    Explanations

    handling conditions and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ary
    0.40
    illons
    0.40
    aufnahme
    0.40
    ini
    0.40
    wy
    0.40
     Supper
    0.39
    itek
    0.39
    itz
    0.39
    useum
    0.38
    uet
    0.38
    POSITIVE LOGITS
     inference
    0.42
    ]=
    0.41
     fanbase
    0.40
     appendage
    0.40
     జి
    0.39
     provision
    0.38
     unravel
    0.38
     amelior
    0.38
     elapse
    0.38
     질
    0.37
    Act Density 0.001%

    No Known Activations