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

    Neuronpedia

    INDEX
    Explanations

    Statements/Assertions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bullet
    -0.08
     tenant
    -0.07
     warrant
    -0.06
    Career
    -0.06
    tica
    -0.06
    pag
    -0.06
     pag
    -0.06
     wildcard
    -0.06
     builders
    -0.06
    …”
    -0.06
    POSITIVE LOGITS
    (金
    0.07
    -instagram
    0.06
    (wx
    0.06
    　i
    0.06
     getY
    0.06
    Disappear
    0.06
    _RATIO
    0.06
     км
    0.06
     대표
    0.06
    .Reflection
    0.06
    Act Density 0.024%

    No Known Activations