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

    Neuronpedia

    INDEX
    Explanations

    comparisons and similarities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )^
    -0.07
     fat
    -0.07
    ちゃん
    -0.06
     ferm
    -0.06
     지역
    -0.06
    .food
    -0.06
    wives
    -0.06
    Wo
    -0.06
    ủy
    -0.06
    commerce
    -0.06
    POSITIVE LOGITS
    _THREAD
    0.07
    .hostname
    0.07
    rai
    0.07
     pev
    0.06
     Detect
    0.06
     участь
    0.06
     Necklace
    0.06
     Jasper
    0.06
     Conexion
    0.06
     trebuie
    0.06
    Act Density 0.009%

    No Known Activations