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

    Neuronpedia

    INDEX
    Explanations

    costing, sports, languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.53
     PHY
    0.52
     align
    0.51
     alignments
    0.51
     Weib
    0.49
    媇
    0.48
     alignment
    0.48
     बुनिया
    0.48
     interpersonal
    0.48
    ству
    0.47
    POSITIVE LOGITS
    غط
    0.50
    ader
    0.46
    chan
    0.44
    ha
    0.44
    ugen
    0.43
    ./
    0.43
    haf
    0.42
    cc
    0.41
    og
    0.41
    adam
    0.41
    Act Density 0.002%

    No Known Activations