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

    Neuronpedia

    INDEX
    Explanations

    Population data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _output
    -0.06
    _ne
    -0.06
    issa
    -0.06
    ieves
    -0.06
     geg
    -0.06
    	se
    -0.06
    -ne
    -0.06
    fw
    -0.06
     Candle
    -0.05
     humble
    -0.05
    POSITIVE LOGITS
    atoon
    0.07
     sized
    0.07
    SCREEN
    0.06
    Peer
    0.06
     Wikip
    0.06
    alc
    0.06
     Talks
    0.06
     アイ
    0.06
    .REG
    0.06
     ileri
    0.06
    Act Density 0.001%

    No Known Activations