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

    Neuronpedia

    INDEX
    Explanations

    definitions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    érard
    0.47
    efined
    0.43
    arm
    0.41
    াউন
    0.40
    ettha
    0.38
    controlling
    0.38
    ifrån
    0.38
     Reprodu
    0.38
    zug
    0.38
    intérieur
    0.38
    POSITIVE LOGITS
    ’,
    0.39
    ,:
    0.39
     outpost
    0.37
    ,’
    0.37
    ’)
    0.36
     HLA
    0.36
     drape
    0.36
     permit
    0.35
     wheelbase
    0.35
    埠
    0.35
    Act Density 0.001%

    No Known Activations