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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Friedrich
    -0.07
     okreś
    -0.06
    .ones
    -0.06
    InParameter
    -0.06
     conjug
    -0.06
     Units
    -0.06
    radius
    -0.06
     parentheses
    -0.06
    漈
    -0.06
    .temp
    -0.06
    POSITIVE LOGITS
     Woodward
    0.07
     backlog
    0.07
     своб
    0.07
    INVALID
    0.07
    rooms
    0.07
    红枣
    0.07
     CREATED
    0.07
     heaps
    0.07
    ánh
    0.07
    submitted
    0.07
    Act Density 0.020%

    No Known Activations