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

    Neuronpedia

    INDEX
    Explanations

    of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रोजगार
    0.47
     نئے
    0.45
     gestão
    0.43
     экскур
    0.43
    เย
    0.43
     новый
    0.43
     სას
    0.43
    robespierre
    0.42
     воспа
    0.42
     quelles
    0.42
    POSITIVE LOGITS
     anything
    0.50
     thisobject
    0.47
     the
    0.47
    thisobject
    0.44
     bromide
    0.43
     object
    0.43
     each
    0.42
     angegeben
    0.42
     your
    0.42
     specified
    0.42
    Act Density 0.197%

    No Known Activations