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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Practices
    -0.08
     watches
    -0.08
    Sens
    -0.07
     Shame
    -0.07
     Recovery
    -0.07
    男女
    -0.07
     apology
    -0.07
     openly
    -0.07
    Recovery
    -0.07
    Distances
    -0.07
    POSITIVE LOGITS
     форму
    0.09
     resembling
    0.09
     fruition
    0.08
     leak
    0.08
     vivid
    0.08
    იონ
    0.08
    含
    0.08
     devi
    0.08
     μορ
    0.08
     resemblance
    0.08
    Act Density 0.023%

    No Known Activations