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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dreaming
    -0.08
     tầng
    -0.06
     mediated
    -0.06
     bore
    -0.06
     contradict
    -0.06
    alem
    -0.06
    oğu
    -0.06
    ologically
    -0.06
     collaborate
    -0.06
    шила
    -0.06
    POSITIVE LOGITS
                
↵
    0.07
    aidu
    0.06
    eware
    0.06
     changes
    0.06
     anonymous
    0.06
    (Call
    0.06
     Biblical
    0.06
    Leg
    0.06
     Exit
    0.06
    Nic
    0.06
    Act Density 0.025%

    No Known Activations