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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cube
    -0.07
    ="{!!
    -0.06
    /lo
    -0.06
    bast
    -0.06
    .Components
    -0.06
    bbie
    -0.06
    Ajax
    -0.06
     ワ
    -0.06
    loggedin
    -0.06
     wissen
    -0.06
    POSITIVE LOGITS
    Government
    0.07
     vegetables
    0.07
     Gov
    0.07
     manipulating
    0.06
    ोड
    0.06
     Vet
    0.06
     enact
    0.06
     join
    0.06
    ambiguous
    0.06
     nud
    0.06
    Act Density 0.001%

    No Known Activations