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

    Neuronpedia

    INDEX
    Explanations

    Galaxie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movimientos
    0.57
     movimentos
    0.57
     opportunities
    0.55
     automatically
    0.54
     Opportunities
    0.54
     Bedingungen
    0.54
     Amounts
    0.53
     asociaciones
    0.52
    чора
    0.52
     hoved
    0.51
    POSITIVE LOGITS
     reminisc
    0.65
     metropolis
    0.63
     doubtless
    0.63
     yr
    0.62
     interplay
    0.62
    若是
    0.62
     reside
    0.62
    咱们
    0.60
    wherein
    0.59
     utilizing
    0.58
    Act Density 0.000%

    No Known Activations