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

    Neuronpedia

    INDEX
    Explanations

    code assignment or status change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    borderColor
    0.96
    кі
    0.93
    лу
    0.89
     Сьогодні
    0.88
    єдна
    0.88
    prese
    0.88
    ло
    0.87
     acqua
    0.86
    adde
    0.86
    endereco
    0.85
    POSITIVE LOGITS
    жной
    0.83
     minimax
    0.83
     كلكم
    0.81
     следующим
    0.80
     mojo
    0.80
     couplings
    0.79
     machined
    0.79
     windings
    0.78
    '
    0.78
     flirt
    0.77
    Act Density 0.001%

    No Known Activations