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

    Neuronpedia

    INDEX
    Explanations

    gender fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.99
    ik
    1.95
    ner
    1.90
    ዖ
    1.82
    вни
    1.79
    ्या
    1.76
    ed
    1.76
    िक
    1.74
     custList
    1.74
    cit
    1.74
    POSITIVE LOGITS
    ㎛
    2.00
    Actress
    1.75
     delighted
    1.72
     Neste
    1.71
    ′,
    1.70
    ″
    1.67
     neste
    1.66
    த்தகைய
    1.64
    plays
    1.61
     همراه
    1.60
    Act Density 0.000%

    No Known Activations