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

    Neuronpedia

    INDEX
    Explanations

    enumerated lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conspiracy
    -0.07
    -ver
    -0.06
    uptools
    -0.06
     SER
    -0.06
    ocity
    -0.06
     �
    -0.06
     serpent
    -0.06
    _cross
    -0.06
     Crime
    -0.06
     Screens
    -0.06
    POSITIVE LOGITS
     immigrants
    0.07
     casos
    0.07
    KF
    0.07
     Watkins
    0.06
     можлив
    0.06
    ่อย
    0.06
     Tap
    0.06
    annie
    0.06
    ackbar
    0.06
     desde
    0.06
    Act Density 0.021%

    No Known Activations