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

    Neuronpedia

    INDEX
    Explanations

    correlation and causation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aqu
    0.50
    D
    0.49
    Ar
    0.47
    Array
    0.46
    Cons
    0.46
    や
    0.46
    Luis
    0.46
    Blob
    0.46
    ५
    0.45
    Assign
    0.44
    POSITIVE LOGITS
     Himalayas
    0.51
     Diary
    0.48
     Chichester
    0.47
     Precambrian
    0.47
     Address
    0.46
     Selector
    0.46
     Lower
    0.45
     Graphical
    0.45
     Himalaya
    0.45
     Chairman
    0.45
    Act Density 0.003%

    No Known Activations