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

    Neuronpedia

    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    疵
    0.74
    엮
    0.74
    Madam
    0.71
     činn
    0.70
    नल
    0.68
    पं
    0.67
     connectors
    0.67
    常量
    0.66
     பொ
    0.66
    ект
    0.66
    POSITIVE LOGITS
     thoải
    0.74
    မျ
    0.69
     pente
    0.69
    vonne
    0.66
    れい
    0.63
     Sommer
    0.63
    🍖
    0.63
    harusnya
    0.62
     mitra
    0.62
     సినిమాలు
    0.61
    Act Density 0.022%

    No Known Activations