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

    Neuronpedia

    INDEX
    Explanations

    est

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wider
    -0.07
    iral
    -0.07
    795
    -0.07
     convin
    -0.07
     null
    -0.07
     Ninh
    -0.07
    (k
    -0.07
     cyan
    -0.06
     coke
    -0.06
     SVM
    -0.06
    POSITIVE LOGITS
    st
    0.13
    ST
    0.11
    est
    0.10
    UST
    0.10
    ust
    0.10
    ст
    0.10
    EST
    0.10
    bst
    0.10
    ost
    0.10
    στα
    0.10
    Act Density 0.348%

    No Known Activations