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

    Neuronpedia

    INDEX
    Explanations

    lifestyle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staats
    -0.08
     Antonio
    -0.08
    Charm
    -0.08
     Univers
    -0.08
     chir
    -0.07
     Dolls
    -0.07
     jig
    -0.07
     تجربة
    -0.07
    Univers
    -0.07
     Hitchcock
    -0.07
    POSITIVE LOGITS
     modifications
    0.09
    因素
    0.08
     factors
    0.08
     instituted
    0.08
     পরিবর্ত
    0.08
     obnov
    0.08
     tweaks
    0.08
    choices
    0.08
     choices
    0.08
     Choices
    0.08
    Act Density 0.004%

    No Known Activations