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

    Neuronpedia

    INDEX
    Explanations

    reliability, handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ět
    -0.07
     dür
    -0.07
    เว
    -0.07
    -meta
    -0.06
     některé
    -0.06
    เหล
    -0.06
    !***
    -0.06
    �
    -0.06
    uo
    -0.06
     NIH
    -0.06
    POSITIVE LOGITS
    ingroup
    0.06
     strconv
    0.06
     fellow
    0.06
    .arr
    0.06
    Declare
    0.06
     baz
    0.06
     roaming
    0.06
    contin
    0.06
     s
    0.06
    .ll
    0.06
    Act Density 0.031%

    No Known Activations