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

    Neuronpedia

    INDEX
    Explanations

    email correspondence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INSTANCE
    -0.07
    xda
    -0.07
     beste
    -0.07
    ดย
    -0.07
    Slave
    -0.07
    免
    -0.07
    ))){↵
    -0.06
    _PRESENT
    -0.06
    icari
    -0.06
    widgets
    -0.06
    POSITIVE LOGITS
    370
    0.07
    ают
    0.07
     contradiction
    0.06
    hazi
    0.06
     coupe
    0.06
    ает
    0.06
    configs
    0.06
    member
    0.06
    яж
    0.06
     affirm
    0.06
    Act Density 0.000%

    No Known Activations