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

    Neuronpedia

    INDEX
    Explanations

    assembly instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inine
    -0.09
    ashboard
    -0.09
    。：
    -0.08
    nne
    -0.08
    imité
    -0.08
    ுவர்
    -0.08
    .algorithm
    -0.08
    inian
    -0.08
    apeau
    -0.08
    ennai
    -0.08
    POSITIVE LOGITS
     preliminary
    0.08
     Alignment
    0.08
     provisional
    0.08
    _alignment
    0.08
    Alignment
    0.08
     vha
    0.08
     alignment
    0.08
    _ALIGNMENT
    0.08
    试
    0.08
     Interim
    0.07
    Act Density 0.007%

    No Known Activations