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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonder
    -0.08
     waard
    -0.07
    ircular
    -0.07
    Overs
    -0.07
     unt
    -0.07
     constantemente
    -0.07
    Compatibility
    -0.07
    >Edit
    -0.07
    Balancer
    -0.07
     pornography
    -0.07
    POSITIVE LOGITS
     capita
    0.11
     euro
    0.09
     రోజు
    0.09
     annum
    0.09
     ఒక్క
    0.09
     woman
    0.08
     রাতে
    0.08
     ತಿಂ
    0.08
     સમયે
    0.08
     se
    0.08
    Act Density 0.047%

    No Known Activations