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

    Neuronpedia

    INDEX
    Explanations

    rou

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {},
    -0.07
    xAD
    -0.07
    ί
    -0.06
    };
↵
    -0.06
    ٥
    -0.06
     ];
↵
    -0.06
    _bbox
    -0.06
     읽
    -0.06
    siyon
    -0.06
    ções
    -0.06
    POSITIVE LOGITS
     Fr
    0.07
     evade
    0.07
     scarf
    0.06
     Fe
    0.06
    leine
    0.06
     Pre
    0.06
     กรกฎ
    0.06
     Guardian
    0.06
     생활
    0.06
     simpler
    0.06
    Act Density 0.006%

    No Known Activations