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

    Neuronpedia

    INDEX
    Explanations

    automake autoconf libtool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éral
    0.81
    에
    0.79
    obec
    0.78
    미
    0.78
    ре
    0.75
    군
    0.75
    伡
    0.75
    신
    0.75
    מד
    0.74
    swürdig
    0.74
    POSITIVE LOGITS
     saxophone
    0.83
     tinge
    0.80
     forearm
    0.79
     stratosphere
    0.77
     crush
    0.77
     upbringing
    0.75
     permangan
    0.75
     stratum
    0.74
     sark
    0.74
     sax
    0.73
    Act Density 0.000%

    No Known Activations