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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bulgaria
    -0.07
     furthermore
    -0.07
    instein
    -0.07
    сом
    -0.06
     phrase
    -0.06
    menin
    -0.06
     Muk
    -0.06
    isque
    -0.06
    rx
    -0.06
     paradigm
    -0.06
    POSITIVE LOGITS
    .tcp
    0.07
     Час
    0.06
     �
    0.06
    _qty
    0.06
     身
    0.06
    vous
    0.06
    .minimum
    0.06
     prostřed
    0.06
    ;left
    0.06
    ็บ
    0.06
    Act Density 0.031%

    No Known Activations