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
    越
    -0.06
     flo
    -0.06
    })();↵↵
    -0.06
     lif
    -0.06
    …↵↵
    -0.06
     З
    -0.06
    _channel
    -0.06
    .)↵↵
    -0.06
     tenga
    -0.05
     prohibited
    -0.05
    POSITIVE LOGITS
    _COUNT
    0.07
     szer
    0.06
     résult
    0.06
     Chew
    0.06
     Rough
    0.06
     Bab
    0.06
    ilibrium
    0.06
     tyre
    0.06
     gibt
    0.06
     atomic
    0.06
    Act Density 0.005%

    No Known Activations