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

    Neuronpedia

    INDEX
    Explanations

    take things your time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xuống
    0.38
    兴趣
    0.37
     downlink
    0.37
     لخ
    0.37
    刺
    0.37
    Arc
    0.37
     αφ
    0.37
     የሆነ
    0.36
     ionization
    0.36
    随着
    0.35
    POSITIVE LOGITS
     baby
    0.77
     Baby
    0.73
    Baby
    0.71
    baby
    0.70
     BABY
    0.64
     बेबी
    0.64
     proceed
    0.53
     Proceed
    0.53
    BAB
    0.52
     breather
    0.51
    Act Density 0.009%

    No Known Activations