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

    Neuronpedia

    INDEX
    Explanations

    categories and statistics related to reproductive health and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    baseline and endline comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.45
     morire
    -0.44
     paznok
    -0.42
     koszulka
    -0.42
     kopling
    -0.42
     bluzka
    -0.41
    ूस
    -0.41
     kapture
    -0.40
     responsab
    -0.39
     perhatian
    -0.39
    POSITIVE LOGITS
     estekak
    0.55
     تضيفلها
    0.54
    MessageOf
    0.49
    таратура
    0.47
     PyTuple
    0.47
    findpost
    0.47
    Hochspringen
    0.46
    __*/
    0.45
     similarly
    0.44
    }${
    0.41
    Act Density 0.070%

    No Known Activations