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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orbit
    -0.06
    신청
    -0.06
     courthouse
    -0.06
     podium
    -0.06
    イド
    -0.06
     енерг
    -0.06
    ุ์
    -0.06
    UTTON
    -0.06
    nerg
    -0.06
     accesses
    -0.06
    POSITIVE LOGITS
    resa
    0.07
    azaar
    0.06
    адження
    0.06
     aseg
    0.06
    ifty
    0.06
    狗
    0.06
    grupo
    0.06
     Rif
    0.06
     рос
    0.06
     вули
    0.06
    Act Density 0.021%

    No Known Activations