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

    Neuronpedia

    INDEX
    Explanations

    Joining clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    herit
    -0.06
    елей
    -0.06
    'R
    -0.06
    Catch
    -0.06
     noting
    -0.06
    -route
    -0.06
     desperate
    -0.06
    /the
    -0.06
    ell
    -0.06
    overe
    -0.06
    POSITIVE LOGITS
     Savage
    0.07
     iş
    0.07
    .age
    0.07
    ยนแปลง
    0.06
     времен
    0.06
     و
    0.06
     gadget
    0.06
     사무
    0.06
     bez
    0.06
    Tes
    0.06
    Act Density 0.000%

    No Known Activations