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

    Neuronpedia

    INDEX
    Explanations

    Identifying pressures or doing good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commas
    0.72
     Opera
    0.70
     impar
    0.68
    ارس
    0.68
     IMC
    0.67
     operas
    0.67
     opera
    0.65
     interests
    0.64
    RIE
    0.64
     Pi
    0.64
    POSITIVE LOGITS
    prefetch
    0.83
    miner
    0.71
    rated
    0.70
    cheap
    0.68
    resolved
    0.68
     zariaden
    0.67
     अट
    0.66
    incorporated
    0.66
    ťaž
    0.65
     jedan
    0.65
    Act Density 0.000%

    No Known Activations