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

    Neuronpedia

    INDEX
    Explanations

    was / is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scholarship
    -0.07
    (src
    -0.07
     ---------
    -0.07
     Then
    -0.06
    τής
    -0.06
     Hotels
    -0.06
    ut
    -0.06
    Phi
    -0.06
    806
    -0.06
     hk
    -0.06
    POSITIVE LOGITS
     "#{
    0.08
    _real
    0.07
    |"
    0.07
         
↵
    0.07
     \''
    0.06
     marched
    0.06
     tercer
    0.06
    yum
    0.06
     '#{
    0.06
    ilst
    0.06
    Act Density 0.075%

    No Known Activations