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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ey
    -0.08
    -arm
    -0.07
    -defense
    -0.07
    _we
    -0.07
    ница
    -0.07
     charges
    -0.06
     cakes
    -0.06
     plotting
    -0.06
     dress
    -0.06
     foot
    -0.06
    POSITIVE LOGITS
     urč
    0.07
    ++↵↵
    0.07
     subtract
    0.07
    !"↵↵
    0.07
    рд
    0.07
    ımıza
    0.06
    _confirmation
    0.06
    ));↵↵↵
    0.06
    ).\
    0.06
    abal
    0.06
    Act Density 0.100%

    No Known Activations