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

    Neuronpedia

    INDEX
    Explanations

    how to do it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     squamous
    0.43
     বর্গ
    0.43
     fish
    0.41
    parse
    0.41
     meat
    0.40
     pork
    0.39
     hallucinations
    0.39
     chicken
    0.39
     praises
    0.39
     NGOs
    0.39
    POSITIVE LOGITS
    ড়
    0.45
     necesitaba
    0.44
    брав
    0.43
     তাছাড়া
    0.42
    чеб
    0.42
    Modeling
    0.42
    舒服
    0.41
     intér
    0.39
    ξεις
    0.39
    인은
    0.39
    Act Density 0.002%

    No Known Activations