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

    Neuronpedia

    INDEX
    Explanations

    act

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /fonts
    -0.07
    юр
    -0.07
    zip
    -0.06
    }'
    -0.06
    })
    -0.06
    };
    -0.06
    .yellow
    -0.06
     جور
    -0.06
    enis
    -0.06
     oy
    -0.06
    POSITIVE LOGITS
    act
    0.08
     κρα
    0.07
     accommod
    0.07
    ству
    0.07
     šk
    0.07
     invoice
    0.07
     sta
    0.06
    ağın
    0.06
    şam
    0.06
    したら
    0.06
    Act Density 0.001%

    No Known Activations