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

    Neuronpedia

    INDEX
    Explanations

    creat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /dev
    -0.08
    娵
    -0.07
    ᴶ
    -0.07
    VK
    -0.07
     blessing
    -0.06
    ⍵
    -0.06
    ≜
    -0.06
    樽
    -0.06
    帑
    -0.06
     MEMORY
    -0.06
    POSITIVE LOGITS
     nhé
    0.08
    idos
    0.08
    _grid
    0.07
    '}>↵
    0.07
    一起去
    0.07
    gles
    0.07
    (tp
    0.07
    ירה
    0.07
     Wir
    0.06
    akit
    0.06
    Act Density 0.003%

    No Known Activations