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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sob
    -0.08
    ekkür
    -0.07
    との
    -0.07
     chast
    -0.07
    έν
    -0.06
    saving
    -0.06
     Περι
    -0.06
     dispar
    -0.06
     auss
    -0.06
    /********
    -0.06
    POSITIVE LOGITS
    Profiles
    0.06
    _resource
    0.06
    opts
    0.06
    움
    0.06
     transaction
    0.06
    uates
    0.06
    ulate
    0.06
     recorded
    0.06
    esi
    0.06
     Mara
    0.06
    Act Density 0.000%

    No Known Activations