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

    Neuronpedia

    INDEX
    Explanations

    relationship between concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acetyl
    0.54
    ိပ်
    0.49
    ho
    0.48
    は
    0.47
    Hou
    0.47
    jo
    0.46
    Jo
    0.46
    hj
    0.44
    हु
    0.44
     petrol
    0.44
    POSITIVE LOGITS
    LOSS
    0.50
     জটিল
    0.47
     Oaxaca
    0.46
    RIOT
    0.46
     waarde
    0.45
     मद्देन
    0.45
    ىم
    0.45
     BLUEN
    0.45
     knife
    0.44
     cadena
    0.44
    Act Density 0.001%

    No Known Activations