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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     such
    -0.07
     Teeth
    -0.06
    (Clone
    -0.06
     Mapper
    -0.06
     Que
    -0.06
     switches
    -0.06
     Flames
    -0.06
    rites
    -0.06
     probes
    -0.06
    &M
    -0.06
    POSITIVE LOGITS
     jlong
    0.07
    ª
    0.07
     |-
    0.06
     iniciar
    0.06
    体系
    0.06
    abilirsiniz
    0.06
    내기
    0.06
    {{--
    0.06
    -hot
    0.06
    主義
    0.06
    Act Density 0.000%

    No Known Activations