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

    Neuronpedia

    INDEX
    Explanations

    division or portion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unternehmens
    0.56
     vorige
    0.52
     arrib
    0.51
     waarde
    0.50
     coisas
    0.49
     ફક્ત
    0.49
    ходя
    0.48
     περιο
    0.48
     одино
    0.48
     ան
    0.48
    POSITIVE LOGITS
    With
    0.61
    G
    0.60
    ली
    0.58
    N
    0.57
    EC
    0.54
    _
    0.54
    WT
    0.54
    D
    0.54
    CI
    0.53
    ई
    0.52
    Act Density 0.000%

    No Known Activations