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

    Neuronpedia

    INDEX
    Explanations

    Rhetoric and figures of speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seventh
    -0.08
     뛰
    -0.07
    _VALID
    -0.07
     Hammer
    -0.07
     бук
    -0.07
    (endpoint
    -0.07
    uku
    -0.06
     bek
    -0.06
    ?>">
    -0.06
    	actual
    -0.06
    POSITIVE LOGITS
     anomal
    0.06
    oliberal
    0.06
     mus
    0.06
     diffic
    0.06
     documenting
    0.06
     inventions
    0.06
     陈
    0.06
     journeys
    0.06
     attribution
    0.06
     대한
    0.06
    Act Density 0.015%

    No Known Activations