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

    Neuronpedia

    INDEX
    Explanations

    Past, present, and "is"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curly
    -0.08
     cannabis
    -0.08
     aceite
    -0.08
     Joc
    -0.08
     potassium
    -0.07
    иний
    -0.07
     Andrew
    -0.07
     comes
    -0.07
     direct
    -0.07
     במיוחד
    -0.07
    POSITIVE LOGITS
     прошлого
    0.12
     الماضية
    0.12
     vergang
    0.11
    future
    0.11
    esterday
    0.11
     verleden
    0.10
     الماضي
    0.10
     minul
    0.10
     भविष्य
    0.10
     미래
    0.10
    Act Density 0.036%

    No Known Activations