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

    Neuronpedia

    INDEX
    Explanations

    indicating or expense with loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bone
    0.51
    Merc
    0.50
    ファイル
    0.48
     shri
    0.46
    嵐
    0.46
     fáj
    0.46
    锅
    0.45
    это
    0.45
     это
    0.44
     tego
    0.44
    POSITIVE LOGITS
    ached
    0.45
    ਕਾਰੀ
    0.41
    royalblue
    0.41
    alfi
    0.38
    itation
    0.38
     pierced
    0.38
     bifur
    0.38
     $)$
    0.37
     putative
    0.37
    div
    0.37
    Act Density 0.005%

    No Known Activations