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

    Neuronpedia

    INDEX
    Explanations

    to achieve, other loans, resume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    綘
    0.24
     અથવા
    0.23
    琙
    0.23
     deberá
    0.23
     ወይም
    0.22
    𝗸
    0.22
    iotsitewise
    0.22
    audioType
    0.22
     جوړونک
    0.21
    咿
    0.21
    POSITIVE LOGITS
     to
    0.28
     one
    0.28
     some
    0.26
     much
    0.26
     half
    0.25
    3
    0.25
     all
    0.25
    4
    0.25
     in
    0.24
     "
    0.24
    Act Density 0.008%

    No Known Activations