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

    Neuronpedia

    INDEX
    Explanations

    employer reference or anomaly detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ເນ
    0.52
     בצ
    0.49
    Spar
    0.46
    ដែលមាន
    0.45
     הכ
    0.44
    受信
    0.44
     bê
    0.44
    𝗘
    0.44
     הד
    0.43
     ظرف
    0.43
    POSITIVE LOGITS
     vault
    0.46
     billing
    0.45
     billet
    0.42
     how
    0.40
     detail
    0.40
     synonym
    0.40
     vaults
    0.39
     money
    0.39
    this
    0.39
     uang
    0.39
    Act Density 0.000%

    No Known Activations