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

    Neuronpedia

    INDEX
    Explanations

    forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USTER
    -0.07
    ANG
    -0.07
     chests
    -0.07
     Booster
    -0.06
    frame
    -0.06
    .definition
    -0.06
     Password
    -0.06
     STOP
    -0.06
    aca
    -0.06
     Support
    -0.06
    POSITIVE LOGITS
    destination
    0.07
     UserProfile
    0.06
     sitesi
    0.06
     Colombian
    0.06
     полез
    0.06
    _BYTES
    0.06
     gia
    0.05
    大阪
    0.05
    미
    0.05
    ้ก
    0.05
    Act Density 0.000%

    No Known Activations