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

    Neuronpedia

    INDEX
    Explanations

    Documentation and remembering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuels
    -0.06
    拉
    -0.06
    _nome
    -0.06
    Evt
    -0.06
     Україна
    -0.06
     Pikachu
    -0.06
     ナ
    -0.06
     Copenhagen
    -0.06
     silah
    -0.06
     hatred
    -0.06
    POSITIVE LOGITS
     γρα
    0.06
    };
↵
↵
    0.06
     adultery
    0.06
     INS
    0.06
     SERIAL
    0.06
    Policy
    0.06
    _INS
    0.06
    ordion
    0.06
    	holder
    0.06
     між
    0.06
    Act Density 0.014%

    No Known Activations