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

    Neuronpedia

    INDEX
    Explanations

    political positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .offsetHeight
    -0.07
     तर
    -0.06
    867
    -0.06
     centerX
    -0.06
    attr
    -0.06
     psycho
    -0.06
    	db
    -0.06
    Parse
    -0.06
     зрост
    -0.06
     стандарт
    -0.06
    POSITIVE LOGITS
     commend
    0.07
     nichž
    0.07
     AUG
    0.06
     eas
    0.06
     Lounge
    0.06
     contrasting
    0.06
    MakeRange
    0.06
    _ASSERT
    0.06
     SUMMARY
    0.06
    ogenous
    0.06
    Act Density 0.010%

    No Known Activations