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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >X
    -0.07
    lineno
    -0.07
     arcs
    -0.06
     seront
    -0.06
    Ini
    -0.06
     bek
    -0.06
    ывая
    -0.06
     bytes
    -0.06
     gigantic
    -0.06
    GeV
    -0.06
    POSITIVE LOGITS
    _bind
    0.07
    }\\
    0.07
     stake
    0.07
    "↵↵↵↵
    0.06
     Sidebar
    0.06
    918
    0.06
     stabilize
    0.06
    .Dispatch
    0.06
     platforms
    0.06
     blackmail
    0.06
    Act Density 0.000%

    No Known Activations