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

    Neuronpedia

    INDEX
    Explanations

    northbound or southbound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blow
    0.68
    Javadoc
    0.67
    ロシア
    0.66
    Nigeria
    0.66
    Cotton
    0.66
    Visited
    0.65
    کہ
    0.65
    Total
    0.64
    Notebook
    0.63
    Binding
    0.63
    POSITIVE LOGITS
     inú
    0.73
    esque
    0.71
     under
    0.66
     aange
    0.64
     strides
    0.64
     miglior
    0.64
     n
    0.63
     gebruiken
    0.62
    很不
    0.62
     gjorde
    0.62
    Act Density 0.000%

    No Known Activations