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

    Neuronpedia

    INDEX
    Explanations

    specific region

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matriz
    0.81
     kür
    0.79
     wsp
    0.74
    맟
    0.74
     Calcular
    0.72
     теат
    0.72
     թվ
    0.71
     compañeros
    0.70
    同期
    0.69
    ărat
    0.69
    POSITIVE LOGITS
    those
    0.74
    Those
    0.72
     gr
    0.72
     abond
    0.72
    sh
    0.71
    Чу
    0.69
     anxious
    0.69
     disgust
    0.68
     diss
    0.68
     marginal
    0.68
    Act Density 0.000%

    No Known Activations