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

    Neuronpedia

    INDEX
    Explanations

    ve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kings
    -0.07
    .roles
    -0.07
    _shapes
    -0.07
    recipient
    -0.07
    orr
    -0.07
    reminder
    -0.07
     Panic
    -0.07
    or
    -0.06
    Temperature
    -0.06
     THEORY
    -0.06
    POSITIVE LOGITS
    ve
    0.07
     pinpoint
    0.06
    !<
    0.06
     Covent
    0.06
     �
    0.06
     вип
    0.06
     lieu
    0.06
    建立
    0.06
    );\
    0.06
    訪
    0.06
    Act Density 0.001%

    No Known Activations