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

    Neuronpedia

    INDEX
    Explanations

    reasons for behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concetto
    0.72
     Tool
    0.71
    的角度
    0.71
    Reason
    0.70
    בח
    0.70
     Carn
    0.69
     ratio
    0.69
     Tools
    0.69
     Ratio
    0.68
     maturities
    0.67
    POSITIVE LOGITS
     why
    0.76
     how
    0.75
     behind
    0.68
    iless
    0.66
     presenting
    0.63
    ractions
    0.62
    posterous
    0.60
     listed
    0.60
     እንዴት
    0.59
    beh
    0.59
    Act Density 0.074%

    No Known Activations