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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maneu
    -0.08
    ("")]↵
    -0.07
    (ns
    -0.07
     �
    -0.07
     블
    -0.06
     scripted
    -0.06
     inspires
    -0.06
    _ANAL
    -0.06
     نح
    -0.06
    ุญาต
    -0.06
    POSITIVE LOGITS
     Clerk
    0.08
    phet
    0.07
    .turn
    0.07
     privileged
    0.06
    Transport
    0.06
    上了
    0.06
     Stockholm
    0.06
    .temperature
    0.06
    REMOTE
    0.06
    maps
    0.06
    Act Density 0.067%

    No Known Activations