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

    Neuronpedia

    INDEX
    Explanations

    I've included / I put together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    presumably
    0.40
     phải
    0.36
    previously
    0.36
     hitherto
    0.35
     Harus
    0.34
    Previously
    0.34
     heretofore
    0.33
     bukanlah
    0.33
     harus
    0.33
    する必要
    0.33
    POSITIVE LOGITS
     gave
    0.66
     wrote
    0.60
     took
    0.56
    wrote
    0.55
     included
    0.54
     telah
    0.54
     suggested
    0.53
     Included
    0.53
     đã
    0.50
     created
    0.50
    Act Density 0.001%

    No Known Activations