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

    Neuronpedia

    INDEX
    Explanations

    "Other" as an option in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кораб
    0.68
     écrire
    0.67
    {
    0.65
    𝗔
    0.64
     lymphomas
    0.64
     mantras
    0.63
    糹
    0.63
     abras
    0.63
     cohom
    0.63
     A
    0.61
    POSITIVE LOGITS
    at
    0.82
    em
    0.80
    en
    0.79
    ap
    0.74
    ate
    0.74
    atur
    0.73
    enan
    0.71
    ast
    0.69
    .”
    0.69
    u
    0.68
    Act Density 0.024%

    No Known Activations