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

    Neuronpedia

    INDEX
    Explanations

    numbers, units, and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.62
     name
    0.48
     front
    0.47
     sf
    0.45
     gén
    0.44
    禳
    0.44
     group
    0.43
     salvar
    0.43
     secures
    0.43
     code
    0.43
    POSITIVE LOGITS
    <unused556>
    0.55
    <unused1014>
    0.54
    <unused1852>
    0.54
     OXIDES
    0.53
    Pul
    0.52
    <unused1086>
    0.52
    ക്ക്
    0.51
    ,’”
    0.51
    <unused612>
    0.50
     reali
    0.49
    Act Density 0.000%

    No Known Activations