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

    Neuronpedia

    INDEX
    Explanations

    sitting at a table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    	head
    -0.06
    ━
    -0.06
    _RECV
    -0.06
    -0.06
    好き
    -0.06
    ynos
    -0.06
    backend
    -0.06
     repell
    -0.06
     phiếu
    -0.05
    POSITIVE LOGITS
     Polo
    0.07
    enn
    0.07
    CRM
    0.07
     JAN
    0.06
     carte
    0.06
    owl
    0.06
    TIM
    0.06
    각
    0.06
     lightly
    0.06
     appearance
    0.06
    Act Density 0.003%

    No Known Activations