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

    Neuronpedia

    INDEX
    Explanations

    printing the head of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >>>
    0.38
     OLD
    0.37
    Ecc
    0.37
     wolf
    0.37
     EVENT
    0.36
     Fed
    0.36
    arent
    0.36
    its
    0.35
    autant
    0.35
    ギュア
    0.35
    POSITIVE LOGITS
    리카
    0.41
     начну
    0.41
     pêche
    0.39
     beauté
    0.39
    ศี
    0.38
    payer
    0.38
    зовая
    0.38
    coaster
    0.37
    showHeader
    0.36
    CallSettings
    0.36
    Act Density 0.000%

    No Known Activations