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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drills
    -0.07
     thoải
    -0.06
     edged
    -0.06
     routed
    -0.06
    _DENIED
    -0.06
     rope
    -0.06
     pistols
    -0.06
    ระหว
    -0.06
     fila
    -0.06
     vùng
    -0.06
    POSITIVE LOGITS
     Amir
    0.06
     cham
    0.06
     mattered
    0.06
    /results
    0.06
     llvm
    0.06
    _ipv
    0.06
     stars
    0.06
    γων
    0.06
    -provider
    0.06
     uphe
    0.06
    Act Density 0.085%

    No Known Activations