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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fully
    0.73
     narrow
    0.72
     engage
    0.71
     eng
    0.70
     shall
    0.68
    ออก
    0.68
     firmly
    0.67
     limited
    0.66
     entr
    0.66
    فه
    0.65
    POSITIVE LOGITS
    utils
    1.03
    tokenizer
    0.99
     lactose
    0.99
    python
    0.94
    LaTeX
    0.93
     solidaridad
    0.92
     latex
    0.91
    ｾ
    0.89
     python
    0.88
     акча
    0.88
    Act Density 0.623%

    No Known Activations