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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sponge
    -0.07
     advertise
    -0.07
     метою
    -0.06
    .Authorization
    -0.06
     hàm
    -0.06
    찬
    -0.06
    แ
    -0.06
    وث
    -0.06
     bfs
    -0.06
    هور
    -0.06
    POSITIVE LOGITS
    ess
    0.07
    *z
    0.07
    appa
    0.07
    validate
    0.06
     colourful
    0.06
    ]',↵
    0.06
    "];
    0.06
     strategies
    0.06
    )</
    0.06
    !==
    0.06
    Act Density 0.001%

    No Known Activations