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

    Neuronpedia

    INDEX
    Explanations

    the word "proper" and closely related words like "correct".

    oai_token-act-pair · gemini-2.0-flash

    proper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.57
    freopen
    -0.50
     GlobalKey
    -0.50
    GetHashCode
    -0.49
    IVEREF
    -0.48
    Odkazy
    -0.47
    ($__
    -0.46
    DataSetChanged
    -0.45
    Földrajzportál
    -0.45
    chauss
    -0.44
    POSITIVE LOGITS
     proper
    1.28
    proper
    1.21
     correct
    1.21
    Proper
    1.14
     Proper
    1.14
     properly
    1.12
     Correct
    1.11
     correctly
    1.07
    correct
    1.06
     PROPER
    1.06
    Act Density 1.307%

    No Known Activations