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

    Neuronpedia

    INDEX
    Explanations

    punctuation and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gosudarstvennyj
    0.45
    𒌆
    0.44
    Sensitivity
    0.44
     सीक्व
    0.42
     अय्यर
    0.41
    Ḥ
    0.40
    𒌅
    0.40
    蘅
    0.40
     renormalized
    0.39
    釟
    0.38
    POSITIVE LOGITS
      
    0.54
    0.45
     varient
    0.43
    👽
    0.42
    uje
    0.41
    ap
    0.40
     Youtube
    0.39
    mo
    0.39
    ovanje
    0.39
    છ
    0.39
    Act Density 0.003%

    No Known Activations