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

    Neuronpedia

    INDEX
    Explanations

    coordinate, bind, wearing, anticipate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅬ
    0.88
     Це
    0.87
     Уже
    0.86
     Technically
    0.83
     stos
    0.82
    на
    0.82
     Fertil
    0.82
    šću
    0.81
    jších
    0.79
     пра
    0.79
    POSITIVE LOGITS
    uelle
    0.70
    ன்
    0.67
    simulation
    0.66
     von
    0.65
    ties
    0.63
     model
    0.63
    erv
    0.62
    err
    0.62
    鑾
    0.62
     islands
    0.61
    Act Density 0.000%

    No Known Activations