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

    Neuronpedia

    INDEX
    Explanations

    actions after "proceeded to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.68
     ANIM
    0.60
    s
    0.60
    GRESS
    0.60
    ENDING
    0.59
    ending
    0.58
    Philos
    0.58
     NDVI
    0.58
    NDAY
    0.58
     If
    0.58
    POSITIVE LOGITS
    로
    0.65
    其他
    0.63
    源
    0.57
    to
    0.54
     sharps
    0.53
    대
    0.53
    です
    0.51
     ubiquitous
    0.51
     rallying
    0.51
    知
    0.50
    Act Density 0.001%

    No Known Activations