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

    Neuronpedia

    INDEX
    Explanations

    segments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ca
    -0.07
     sparks
    -0.07
     shielding
    -0.07
    دام
    -0.06
     tại
    -0.06
     örnek
    -0.06
     하지만
    -0.06
    아
    -0.06
     nối
    -0.06
     computation
    -0.06
    POSITIVE LOGITS
     �
    0.06
     exec
    0.06
     xxx
    0.06
    \↵
    0.06
    られる
    0.06
    مس
    0.06
     xx
    0.06
    _First
    0.06
    !';↵
    0.05
    .indent
    0.05
    Act Density 1.022%

    No Known Activations