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

    Neuronpedia

    INDEX
    Explanations

    queries/prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nett
    -0.07
     ]↵↵↵
    -0.07
    ),↵
    -0.06
     atas
    -0.06
    )],↵
    -0.06
    ),↵↵
    -0.06
    mount
    -0.06
     decade
    -0.06
     pratique
    -0.06
     NF
    -0.06
    POSITIVE LOGITS
     Cory
    0.07
     선수
    0.06
     Moved
    0.06
    _handler
    0.06
    MeshPro
    0.06
    _mutex
    0.06
    wallet
    0.06
    :string
    0.06
     Conserv
    0.06
     glamour
    0.06
    Act Density 0.001%

    No Known Activations