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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fdPar
    0.92
    готовить
    0.89
     сегодняш
    0.86
     Carpath
    0.86
     выполнить
    0.86
     обновления
    0.85
    孅
    0.84
     basados
    0.84
     слишком
    0.84
     eigenstates
    0.83
    POSITIVE LOGITS
    0.91
    ps
    0.82
    ism
    0.78
    il
    0.73
    ers
    0.71
    ts
    0.70
    ting
    0.70
    帷
    0.69
     dos
    0.68
     there
    0.68
    Act Density 0.001%

    No Known Activations