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

    Neuronpedia

    INDEX
    Explanations

    nice to meet you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    з
    0.51
    白
    0.48
     mortalidad
    0.48
    ста
    0.46
     carp
    0.46
     sarees
    0.46
    尅
    0.45
    ਸ
    0.45
    指令
    0.45
     किस्त
    0.45
    POSITIVE LOGITS
     extol
    0.43
    phant
    0.40
    ettes
    0.40
    ennes
    0.40
     scoff
    0.39
    cuss
    0.39
    cent
    0.39
    healthy
    0.38
     fasting
    0.38
     pouring
    0.38
    Act Density 0.056%

    No Known Activations