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

    Neuronpedia

    INDEX
    Explanations

    financial, json, and code configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tasteless
    0.69
    ivorous
    0.66
    謚
    0.65
    steal
    0.65
    嵊
    0.65
    횡
    0.64
    がる
    0.64
    hensible
    0.64
     persönliche
    0.63
    บุคคล
    0.63
    POSITIVE LOGITS
    ৭
    0.71
    જર
    0.66
     Banking
    0.65
     Donations
    0.64
     ഇതു
    0.63
     julho
    0.63
    Within
    0.62
    Nft
    0.61
             
    0.61
    cpf
    0.60
    Act Density 0.048%

    No Known Activations