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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    놉
    -0.08
    끗
    -0.07
    .Nombre
    -0.07
    碹
    -0.07
    嶒
    -0.07
    низ
    -0.07
    .Env
    -0.07
    疱
    -0.07
     foreigners
    -0.07
    酆
    -0.07
    POSITIVE LOGITS
     secured
    0.07
     activity
    0.07
    emed
    0.07
    usiness
    0.07
     carried
    0.07
    oved
    0.07
     gradually
    0.07
    Nos
    0.07
    .Real
    0.07
     Ref
    0.07
    Act Density 0.208%

    No Known Activations