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

    Neuronpedia

    INDEX
    Explanations

    Artem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flange
    -0.08
    ?>
    -0.08
     VIC
    -0.07
     "_"
    -0.07
     willingness
    -0.07
     smoothly
    -0.07
                  ↵
    -0.07
    ?>↵
    -0.07
     calculator
    -0.07
     errors
    -0.07
    POSITIVE LOGITS
    Kid
    0.09
     Elena
    0.09
    पाल
    0.08
    Titles
    0.08
    kid
    0.08
     Giovanni
    0.08
     kid
    0.08
    御
    0.07
     Julia
    0.07
     Ear
    0.07
    Act Density 0.002%

    No Known Activations