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

    Neuronpedia

    INDEX
    Explanations

    POST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "d
    -0.07
    ampie
    -0.07
     Taxes
    -0.07
     chí
    -0.06
    _Date
    -0.06
    ��
    -0.06
     Sahara
    -0.06
    Sm
    -0.06
    िं
    -0.06
     Dân
    -0.06
    POSITIVE LOGITS
     grayscale
    0.08
    ocked
    0.07
    OTO
    0.06
    žel
    0.06
    _supply
    0.06
    uts
    0.06
     unclear
    0.06
    (vars
    0.06
     skulls
    0.06
    BERS
    0.06
    Act Density 0.001%

    No Known Activations