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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聚
    -0.07
    reading
    -0.07
    工程
    -0.07
     ecstasy
    -0.07
    .title
    -0.07
    Feel
    -0.06
    _Rem
    -0.06
    ốn
    -0.06
    pire
    -0.06
     meanings
    -0.06
    POSITIVE LOGITS
     Executors
    0.07
    /Main
    0.06
    	timeout
    0.06
     Elf
    0.06
    ・ア
    0.06
     unnecessarily
    0.06
     APPLE
    0.06
     ordin
    0.06
     ElseIf
    0.06
     \'
    0.06
    Act Density 0.005%

    No Known Activations