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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	glm
    -0.07
    _reservation
    -0.07
     matrices
    -0.07
    radient
    -0.07
    aises
    -0.07
     Bags
    -0.06
     localization
    -0.06
    paces
    -0.06
     crave
    -0.06
     genomes
    -0.06
    POSITIVE LOGITS
     viewBox
    0.07
    έ
    0.07
     Messenger
    0.07
    .policy
    0.07
    ANN
    0.06
     shrine
    0.06
    essenger
    0.06
     outputFile
    0.06
     CREATED
    0.06
    	html
    0.06
    Act Density 0.080%

    No Known Activations