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

    Neuronpedia

    INDEX
    Explanations

    Legal context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geç
    -0.07
    $/
    -0.07
     },{
    -0.06
    人在
    -0.06
     Nobody
    -0.06
    �
    -0.06
     !
    -0.06
     Give
    -0.06
     inconvenience
    -0.06
    %C
    -0.06
    POSITIVE LOGITS
    峗
    0.07
    росс
    0.07
     Trails
    0.07
    溹
    0.07
    VEST
    0.07
    焗
    0.07
    _Trans
    0.07
    텁
    0.06
    觚
    0.06
    悆
    0.06
    Act Density 0.123%

    No Known Activations