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

    Neuronpedia

    INDEX
    Explanations

    consequence or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optionally
    0.45
     Everybody
    0.39
     periodically
    0.38
     compared
    0.37
    ReferencePose
    0.37
    endum
    0.37
    olip
    0.37
     bothers
    0.37
     versus
    0.36
     сравни
    0.36
    POSITIVE LOGITS
    随着
    0.63
    隨著
    0.59
     вследствие
    0.58
     akibat
    0.55
    经过
    0.52
    จากการ
    0.52
    Through
    0.51
    Increased
    0.51
     dzięki
    0.50
     durch
    0.50
    Act Density 0.020%

    No Known Activations