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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destabil
    -0.06
    Untitled
    -0.06
     技
    -0.06
     anth
    -0.06
     urg
    -0.06
     =================================================================
    -0.06
     unsere
    -0.06
    =''
    -0.06
    <Order
    -0.06
    )?↵↵
    -0.06
    POSITIVE LOGITS
    prep
    0.07
     Mal
    0.06
     gunman
    0.06
     assumptions
    0.06
    GREEN
    0.06
     funding
    0.06
     triplet
    0.06
     سام
    0.06
     نگ
    0.06
     wrongly
    0.06
    Act Density 0.000%

    No Known Activations