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

    Neuronpedia

    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    인트
    -0.07
    Reset
    -0.07
    _None
    -0.07
    (horizontal
    -0.07
    _PK
    -0.07
    จะต
    -0.07
    Hook
    -0.07
    research
    -0.07
     Vaugh
    -0.06
     Ebook
    -0.06
    POSITIVE LOGITS
     Equ
    0.07
     Sim
    0.06
    ubectl
    0.06
     یوتی
    0.06
    ],"
    0.06
    
    0.06
     terr
    0.06
    .Details
    0.05
     condol
    0.05
    .serial
    0.05
    Act Density 0.004%

    No Known Activations