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

    Neuronpedia

    INDEX
    Explanations

    Web links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    York
    -0.06
    �
    -0.06
    _web
    -0.06
    ffen
    -0.06
    buah
    -0.06
     Crisis
    -0.06
    servername
    -0.06
     Officer
    -0.06
    레벨
    -0.06
    ,<
    -0.06
    POSITIVE LOGITS
     lingu
    0.08
    ”—
    0.07
    	PORT
    0.07
     turn
    0.07
     Moor
    0.06
    .visitMethod
    0.06
     formulario
    0.06
     якості
    0.06
    (img
    0.06
     burning
    0.06
    Act Density 0.011%

    No Known Activations