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

    Neuronpedia

    INDEX
    Explanations

    code or dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uckles
    -0.07
    fram
    -0.07
    ата
    -0.07
     plight
    -0.06
     operands
    -0.06
     victims
    -0.06
     accessories
    -0.06
    _tw
    -0.06
     unl
    -0.06
    Executive
    -0.06
    POSITIVE LOGITS
    _ENTRY
    0.07
     формування
    0.06
    (nameof
    0.06
     vagina
    0.06
    ')↵↵
    0.06
     西
    0.06
     protocol
    0.06
    (argument
    0.06
    ]</
    0.06
    圣
    0.06
    Act Density 0.001%

    No Known Activations