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

    Neuronpedia

    INDEX
    Explanations

    categorical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hydraulic
    -0.08
    idelberg
    -0.08
    😮
    -0.08
    reiben
    -0.07
    (cd
    -0.07
     concurrently
    -0.07
     onSuccess
    -0.07
    䗛
    -0.07
     {}),↵
    -0.07
     [])
    -0.07
    POSITIVE LOGITS
    忠实
    0.07
    -input
    0.07
    כלל
    0.07
     civilian
    0.07
    STRING
    0.07
    .Content
    0.07
     disgu
    0.06
    认识到
    0.06
     налич
    0.06
     סרט
    0.06
    Act Density 0.001%

    No Known Activations