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

    Neuronpedia

    INDEX
    Explanations

    creating subsequent states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plus
    1.27
     which
    1.15
     coupled
    1.07
     includes
    1.05
     versus
    1.01
     along
    1.01
     associated
    0.99
     involves
    0.99
     alongside
    0.98
     include
    0.97
    POSITIVE LOGITS
    creating
    1.33
     creando
    1.22
     creating
    1.14
    ając
    1.11
    Creating
    1.10
    bringing
    1.08
    causing
    1.06
    adding
    1.03
    νοντας
    1.03
     bringing
    1.02
    Act Density 0.313%

    No Known Activations