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

    Neuronpedia

    INDEX
    Explanations

    rs identifiers or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieci
    0.41
     advocates
    0.40
     skeptic
    0.39
     liter
    0.39
     dozen
    0.38
    anei
    0.38
    ഞ്ച്
    0.38
    alá
    0.37
    十五
    0.36
     பத்து
    0.36
    POSITIVE LOGITS
    XXXX
    0.75
     ১৩২২
    0.75
    xxxx
    0.72
    xxxxx
    0.66
    9
    0.63
     १८४
    0.61
     ১৩২১
    0.59
    7
    0.59
    8
    0.57
    १८४
    0.57
    Act Density 0.073%

    No Known Activations