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

    Neuronpedia

    INDEX
    Explanations

    serving and daily dose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     売
    0.55
    ENGTH
    0.49
     believing
    0.48
     इजीली
    0.47
     simpler
    0.45
    melting
    0.44
     jealous
    0.43
     chasing
    0.43
    ั
    0.43
    㶲
    0.43
    POSITIVE LOGITS
    多
    0.47
     altres
    0.47
    ي
    0.47
     sân
    0.46
    男
    0.45
    विव
    0.44
    ;
    0.44
    κολ
    0.43
    就是
    0.42
    允
    0.42
    Act Density 0.001%

    No Known Activations