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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competence
    -0.07
    浮现
    -0.07
    _nth
    -0.07
    _lift
    -0.07
    属性
    -0.07
    invitation
    -0.06
    laps
    -0.06
     crafted
    -0.06
    elseif
    -0.06
     assortment
    -0.06
    POSITIVE LOGITS
     alışver
    0.07
    mock
    0.07
     pepper
    0.07
    ᴖ
    0.07
    篷
    0.07
    Prostit
    0.06
    喁
    0.06
    \/\/
    0.06
    ナン
    0.06
     Doc
    0.06
    Act Density 0.026%

    No Known Activations