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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _contents
    -0.06
    .exists
    -0.06
     constitu
    -0.06
     Stevens
    -0.06
    Retrieve
    -0.06
    chos
    -0.05
     お
    -0.05
    (text
    -0.05
    руч
    -0.05
    necessary
    -0.05
    POSITIVE LOGITS
     pellet
    0.07
     usern
    0.06
     رنگ
    0.06
    der
    0.06
    POSITION
    0.06
     då
    0.06
    emi
    0.06
    纸
    0.06
    allis
    0.06
     Archives
    0.06
    Act Density 0.212%

    No Known Activations