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

    Neuronpedia

    INDEX
    Explanations

    tidying

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एर
    0.65
     comunitario
    0.61
     પ્રકાર
    0.60
    comstock
    0.59
     aperta
    0.58
     aperto
    0.57
     negocio
    0.56
    চাল
    0.56
     działa
    0.55
     VISA
    0.55
    POSITIVE LOGITS
     tid
    0.70
    byshev
    0.59
    参
    0.59
     bitten
    0.56
     PE
    0.55
    以来
    0.55
     fork
    0.55
     turnout
    0.55
     whitew
    0.55
     হায়
    0.53
    Act Density 0.001%

    No Known Activations