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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    389
    -0.08
    FAILURE
    -0.07
    .Emit
    -0.06
     dumped
    -0.06
    ]+'
    -0.06
    bin
    -0.06
     numberWith
    -0.06
     ciz
    -0.06
     are
    -0.06
     having
    -0.06
    POSITIVE LOGITS
    ',...↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    _pose
    0.06
    ivityManager
    0.06
     MUCH
    0.06
    tingham
    0.06
    政
    0.06
     nachází
    0.06
    pressor
    0.06
    sdale
    0.06
    Act Density 0.000%

    No Known Activations