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

    Neuronpedia

    INDEX
    Explanations

    purpose or goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.75
    ,
    0.69
    ?
    0.64
    ".
    0.57
    -
    0.57
    ;
    0.57
    +
    0.56
    ic
    0.55
     ,
    0.53
    !
    0.53
    POSITIVE LOGITS
     mitigate
    0.67
     facilitate
    0.63
     alleviate
    0.63
     enhance
    0.61
     optimize
    0.61
     appease
    0.60
    ppled
    0.60
     ensure
    0.59
     accommodate
    0.58
     achieve
    0.57
    Act Density 0.072%

    No Known Activations