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

    Neuronpedia

    INDEX
    Explanations

    safety guidelines and prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    糅
    0.75
     setia
    0.73
     customize
    0.72
    miR
    0.72
    aaS
    0.71
     customise
    0.71
    aneity
    0.71
    ก็จะ
    0.70
    맛집
    0.70
    Interestingly
    0.69
    POSITIVE LOGITS
     NEVER
    1.53
     Never
    1.47
    Never
    1.44
     never
    1.40
    never
    1.27
     supervision
    1.27
     Supervision
    1.26
     supervise
    1.21
     nunca
    1.21
     supervised
    1.17
    Act Density 0.154%

    No Known Activations