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

    Neuronpedia

    INDEX
    Explanations

    .py

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '<
    -0.06
    _PARAM
    -0.06
    Workers
    -0.06
     parms
    -0.06
    uddle
    -0.06
    291
    -0.06
    ]",
    -0.06
    };↵↵↵↵
    -0.06
     ⟨
    -0.06
    Format
    -0.06
    POSITIVE LOGITS
     хими
    0.07
     prez
    0.07
     cracking
    0.07
    ultiply
    0.06
     فريق
    0.06
    acia
    0.06
     उम
    0.06
     clim
    0.06
    露
    0.06
     prés
    0.06
    Act Density 0.008%

    No Known Activations