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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -used
    -0.07
    deque
    -0.07
    ',['../
    -0.06
     dando
    -0.06
     besser
    -0.06
    altern
    -0.06
     باغ
    -0.06
     gev
    -0.06
     Elem
    -0.06
     Cairo
    -0.06
    POSITIVE LOGITS
    +c
    0.07
     expenditures
    0.07
    .By
    0.07
     wearing
    0.07
     massive
    0.07
     sofa
    0.07
    Picker
    0.07
     note
    0.07
     speaking
    0.07
    directories
    0.06
    Act Density 0.009%

    No Known Activations