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

    Neuronpedia

    INDEX
    Explanations

    here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐠
    0.90
    𝐧
    0.90
    ɴ
    0.84
    𝐛
    0.80
    𝘤
    0.79
    Ꮯ
    0.79
    సూరు
    0.77
    時に
    0.77
    im
    0.76
    neux
    0.76
    POSITIVE LOGITS
     superconduct
    0.98
    abouts
    0.89
    ১
    0.80
    0.79
    }|^
    0.77
     dinyatakan
    0.77
    0.77
    brew
    0.76
     milieu
    0.75
    ء
    0.75
    Act Density 0.039%

    No Known Activations