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
    ナ
    -0.08
     �
    -0.07
     mell
    -0.07
     وبين
    -0.07
     din
    -0.07
    Miss
    -0.07
    _Send
    -0.07
     Ha
    -0.07
    亞
    -0.07
    stration
    -0.07
    POSITIVE LOGITS
    醭
    0.07
    .FromResult
    0.07
    orgt
    0.07
    珢
    0.07
    uela
    0.07
     zwłas
    0.07
     jr
    0.07
    ]")]↵
    0.07
    桷
    0.07
     Mori
    0.07
    Act Density 0.069%

    No Known Activations