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

    Neuronpedia

    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increased
    -0.07
     bigger
    -0.07
    Shield
    -0.07
     二
    -0.06
     embraces
    -0.06
     embraced
    -0.06
     sehr
    -0.06
    Enterprise
    -0.06
    +='<
    -0.06
    })}↵
    -0.06
    POSITIVE LOGITS
     Covent
    0.07
     novel
    0.07
    -dev
    0.07
    카지노
    0.07
    CLE
    0.06
     هل
    0.06
    ovel
    0.06
     Novel
    0.06
    AGED
    0.06
    VICES
    0.06
    Act Density 0.009%

    No Known Activations