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

    Neuronpedia

    INDEX
    Explanations

    decent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Au
    -0.07
    片
    -0.06
    IFICATION
    -0.06
    }`)↵
    -0.06
    ryption
    -0.06
    INU
    -0.06
    .raises
    -0.06
    όγ
    -0.06
    Chart
    -0.06
     ihtiy
    -0.06
    POSITIVE LOGITS
     monstrous
    0.08
     �
    0.08
     Dek
    0.08
    适
    0.07
    -C
    0.07
     decent
    0.07
     descendant
    0.07
     맞
    0.07
     comfortable
    0.07
     patriotism
    0.07
    Act Density 0.003%

    No Known Activations