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

    Neuronpedia

    INDEX
    Explanations

    defend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crunch
    -0.07
    ijkstra
    -0.07
    大き
    -0.06
    -cost
    -0.06
    Massage
    -0.06
     cata
    -0.06
    ahlen
    -0.06
    орту
    -0.06
    сього
    -0.06
     Compression
    -0.06
    POSITIVE LOGITS
     defended
    0.10
     defending
    0.08
     Decompiled
    0.07
     理
    0.07
     武
    0.07
    ắc
    0.07
    ้องก
    0.07
     &&
↵
    0.07
     ﾊ
    0.07
     darn
    0.07
    Act Density 0.013%

    No Known Activations