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

    Neuronpedia

    INDEX
    Explanations

    worth it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ell
    0.38
    Land
    0.37
    should
    0.37
    Willow
    0.36
    things
    0.36
    maps
    0.35
     Needs
    0.35
     Things
    0.35
    successfully
    0.35
    needs
    0.35
    POSITIVE LOGITS
     esfuerzo
    0.55
     effort
    0.54
     perju
    0.50
     consideration
    0.49
    努力
    0.48
     splurge
    0.47
     pena
    0.47
     invester
    0.46
     considerar
    0.45
     investi
    0.45
    Act Density 0.003%

    No Known Activations