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

    Neuronpedia

    INDEX
    Explanations

    DI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pink
    -0.07
    aware
    -0.07
     vont
    -0.07
    ót
    -0.07
    ่วง
    -0.07
     angel
    -0.07
    .calc
    -0.06
    Therefore
    -0.06
     rigorous
    -0.06
    verification
    -0.06
    POSITIVE LOGITS
    <|end_of_text|>
    0.07
    )}"↵
    0.07
    ubs
    0.06
     Ammo
    0.06
    ($('.
    0.06
     Biblical
    0.06
    ')">
    0.06
     Credential
    0.06
     ／
    0.06
     ACPI
    0.06
    Act Density 0.005%

    No Known Activations