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
     All
    -0.07
     Just
    -0.07
    oles
    -0.07
     �
    -0.07
     reveal
    -0.07
    _pwd
    -0.06
    .notice
    -0.06
     plac
    -0.06
     нап
    -0.06
     layers
    -0.06
    POSITIVE LOGITS
    _argv
    0.07
    conj
    0.07
    ↵↵↵↵↵↵↵↵
    0.07
    ugh
    0.06
    )↵↵↵↵↵↵
    0.06
     bağır
    0.06
    ATIVE
    0.06
     золот
    0.06
     사망
    0.06
    拥有
    0.06
    Act Density 0.137%

    No Known Activations