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

    Neuronpedia

    INDEX
    Explanations

    surplus value, regardless, road construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pasando
    0.94
     incluidas
    0.91
     vybaven
    0.91
     moverse
    0.89
     وما
    0.87
     montaña
    0.86
     conocidas
    0.85
    ApiCalls
    0.84
     luchar
    0.84
     necesitar
    0.84
    POSITIVE LOGITS
    TH
    0.75
    та
    0.75
    PRO
    0.72
     opted
    0.70
    GING
    0.69
     gated
    0.68
    OPTIM
    0.68
     researcher
    0.68
    Rush
    0.67
     total
    0.66
    Act Density 0.006%

    No Known Activations