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

    Neuronpedia

    INDEX
    Explanations

    ires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    ANY
    -0.06
     memoria
    -0.06
     Frau
    -0.06
    -di
    -0.06
    "That
    -0.06
    ΥΣ
    -0.06
    eckého
    -0.06
     RW
    -0.06
     CEO
    -0.05
    POSITIVE LOGITS
    Dream
    0.07
    ICE
    0.06
    ální
    0.06
    Sleep
    0.06
     человека
    0.06
     Vik
    0.06
     thirty
    0.06
     Colombia
    0.06
    ूसर
    0.06
     inherited
    0.06
    Act Density 0.000%

    No Known Activations