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

    Neuronpedia

    INDEX
    Explanations

    Street

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mandal
    -0.07
    Others
    -0.07
    ้าหน
    -0.07
    _seat
    -0.07
    */)
    -0.06
    _RST
    -0.06
     béné
    -0.06
    _nama
    -0.06
     mogul
    -0.06
     hugs
    -0.06
    POSITIVE LOGITS
     porous
    0.06
     socialism
    0.06
     applying
    0.06
    าย
    0.06
     υπ
    0.06
     Pierre
    0.06
    يرا
    0.06
     shielding
    0.06
     tyranny
    0.06
    Insensitive
    0.06
    Act Density 0.000%

    No Known Activations