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

    Neuronpedia

    INDEX
    Explanations

    Sheriff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хто
    -0.06
     perpetr
    -0.06
    �
    -0.06
     воз
    -0.06
     лож
    -0.06
    Markers
    -0.06
    Scores
    -0.06
    :expr
    -0.06
     Hugo
    -0.06
    iná
    -0.06
    POSITIVE LOGITS
    τητα
    0.08
     convers
    0.07
     Checking
    0.07
     vidé
    0.07
     boundary
    0.07
     indefinite
    0.07
     neighbours
    0.06
    ordinates
    0.06
    icles
    0.06
    scalar
    0.06
    Act Density 0.007%

    No Known Activations