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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Before
    -0.08
    density
    -0.07
    /manual
    -0.07
    画
    -0.07
     Adoption
    -0.07
     express
    -0.07
     missing
    -0.07
     placeholders
    -0.07
     Reading
    -0.07
    WASHINGTON
    -0.07
    POSITIVE LOGITS
     drawbacks
    0.07
    쎅
    0.07
    抠
    0.07
    _tele
    0.06
    .Keys
    0.06
    _obj
    0.06
    บางคน
    0.06
    Authenticated
    0.06
    🚦
    0.06
    olla
    0.06
    Act Density 0.048%

    No Known Activations