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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Protein
    0.68
     Protein
    0.68
    nP
    0.66
     PROTE
    0.66
     protein
    0.64
     Bit
    0.62
    pern
    0.62
     Před
    0.62
     parted
    0.61
    පු
    0.60
    POSITIVE LOGITS
    sigs
    0.68
    char
    0.67
    opensource
    0.65
    sig
    0.63
     sig
    0.58
    osa
    0.57
    iscope
    0.56
    싯
    0.56
    chr
    0.53
    ্ডি
    0.52
    Act Density 0.324%

    No Known Activations