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

    Neuronpedia

    INDEX
    Explanations

    formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сим
    -0.07
     Translation
    -0.07
    _sat
    -0.06
     Protected
    -0.06
    _widgets
    -0.06
     Marxist
    -0.06
     fins
    -0.06
     vv
    -0.06
    qc
    -0.06
    	my
    -0.06
    POSITIVE LOGITS
    dart
    0.07
    _dice
    0.07
    JE
    0.06
     educator
    0.06
    CLUS
    0.06
    amen
    0.06
    ape
    0.06
     Genius
    0.06
    leneck
    0.06
    .Put
    0.06
    Act Density 0.000%

    No Known Activations