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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kapsamında
    0.45
     Criteria
    0.40
     való
    0.39
     Ideally
    0.39
    oxicity
    0.39
    SI
    0.38
     relativa
    0.38
    ोल
    0.38
     EDI
    0.38
    SA
    0.38
    POSITIVE LOGITS
    पणे
    0.61
    ي
    0.48
    i
    0.46
     допол
    0.40
    addSubview
    0.38
    iénd
    0.36
     forbade
    0.36
    ి
    0.36
    󠁢
    0.36
    '});
    0.35
    Act Density 0.130%

    No Known Activations