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

    Neuronpedia

    INDEX
    Explanations

    poems/lyrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Where
    -0.07
    ifs
    -0.07
     leans
    -0.06
    办
    -0.06
     Le
    -0.06
    Implementation
    -0.06
     restrictions
    -0.06
    Le
    -0.06
    店
    -0.06
    ụ
    -0.06
    POSITIVE LOGITS
     Roof
    0.07
    .…↵↵
    0.07
    tesy
    0.07
     ΑΠ
    0.06
     \""
    0.06
     vyh
    0.06
    .FromSeconds
    0.06
     pravděpodob
    0.06
     Aleppo
    0.06
    矢
    0.06
    Act Density 0.092%

    No Known Activations