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
     thư
    -0.07
    }\"
    -0.07
     stove
    -0.07
    moved
    -0.07
     }}/
    -0.07
    ?>↵
    -0.07
    _Man
    -0.06
    ###
    -0.06
     Mets
    -0.06
     tipped
    -0.06
    POSITIVE LOGITS
     соответств
    0.06
    след
    0.06
     существ
    0.06
    がい
    0.06
    _lineno
    0.06
     इसल
    0.06
    -secret
    0.06
    LL
    0.06
    =e
    0.06
     ofrece
    0.06
    Act Density 0.001%

    No Known Activations