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

    Neuronpedia

    INDEX
    Explanations

    admit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pop
    -0.06
    oters
    -0.06
     chu
    -0.06
    ज़
    -0.06
     purse
    -0.06
    ательных
    -0.06
    Pos
    -0.06
     Ron
    -0.06
    azor
    -0.06
     крем
    -0.06
    POSITIVE LOGITS
    ynchronized
    0.07
     native
    0.07
    157
    0.07
    /right
    0.06
    .station
    0.06
    creation
    0.06
    _PR
    0.06
    ЕТ
    0.06
    _SPE
    0.06
     Weiter
    0.06
    Act Density 0.008%

    No Known Activations