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

    Neuronpedia

    INDEX
    Explanations

    what is the function of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.44
    id
    0.44
     ‘
    0.43
    path
    0.42
    ak
    0.41
    ed
    0.40
    ic
    0.39
    it
    0.38
     Bottle
    0.38
     Cognito
    0.37
    POSITIVE LOGITS
     masing
    0.49
     jeweiligen
    0.48
     respectivos
    0.46
    それぞれ
    0.46
     각각
    0.45
     ngunit
    0.43
    rieron
    0.43
     amines
    0.41
     quelcon
    0.41
     respectiv
    0.41
    Act Density 0.013%

    No Known Activations