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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diferente
    -0.07
     hatta
    -0.07
     Gerard
    -0.07
    Stick
    -0.06
     }))
    -0.06
    peace
    -0.06
     hosts
    -0.06
    .JComboBox
    -0.06
    ně
    -0.06
    нина
    -0.06
    POSITIVE LOGITS
    ğü
    0.07
    (robot
    0.07
    SCRIBE
    0.06
     ====
    0.06
    ΟΤ
    0.06
    원을
    0.06
    \uC
    0.06
    unsupported
    0.06
     XR
    0.06
    PEAR
    0.06
    Act Density 0.267%

    No Known Activations