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

    Neuronpedia

    INDEX
    Explanations

    user principal name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplemente
    0.46
    simply
    0.45
     simply
    0.43
     simplement
    0.41
    zept
    0.41
     semplicemente
    0.40
     gewoon
    0.40
    wość
    0.40
     стаў
    0.39
     powinien
    0.39
    POSITIVE LOGITS
     Theology
    0.43
     Finding
    0.43
    enian
    0.41
     workspaces
    0.40
     Email
    0.40
     남아
    0.38
    обходи
    0.38
     Thousands
    0.38
    odim
    0.38
     Suffering
    0.37
    Act Density 0.003%

    No Known Activations