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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -radio
    -0.07
    basis
    -0.06
    çuk
    -0.06
     прием
    -0.06
    时间
    -0.06
     мот
    -0.06
    елич
    -0.06
     by
    -0.06
    iversary
    -0.06
     enumerator
    -0.06
    POSITIVE LOGITS
    oggled
    0.07
    itled
    0.06
     sensitive
    0.06
    MED
    0.06
    ()][
    0.06
    介
    0.06
    	conn
    0.06
    Ctx
    0.06
    ';↵↵↵
    0.06
    .put
    0.06
    Act Density 0.001%

    No Known Activations