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

    Neuronpedia

    INDEX
    Explanations

    Therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    итися
    -0.07
    -op
    -0.07
    isable
    -0.06
     past
    -0.06
     head
    -0.06
    sys
    -0.06
     pop
    -0.06
    LinkedList
    -0.06
     Blonde
    -0.06
    ’all
    -0.06
    POSITIVE LOGITS
     therefore
    0.10
    Therefore
    0.09
     Therefore
    0.09
    .So
    0.08
    護
    0.07
    -‐
    0.07
     IndexError
    0.07
     THEORY
    0.07
     quindi
    0.07
    stanbul
    0.07
    Act Density 0.023%

    No Known Activations