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

    Neuronpedia

    INDEX
    Explanations

    to communicate or act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arriver
    0.43
     favoring
    0.39
     favour
    0.37
    提到
    0.36
     sugger
    0.36
     arriving
    0.36
    保持
    0.36
     arriva
    0.36
     varia
    0.36
     hinting
    0.36
    POSITIVE LOGITS
     discuss
    0.61
     chat
    0.57
     inspect
    0.54
     assess
    0.53
     personally
    0.52
     listen
    0.51
     talk
    0.50
     persönlich
    0.46
     greet
    0.46
     oversee
    0.46
    Act Density 0.018%

    No Known Activations