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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Important
    0.61
    IMPORTANT
    0.55
    important
    0.54
     componentes
    0.54
     Important
    0.53
    𒈨
    0.52
    ユーザ
    0.52
     componenti
    0.50
     Components
    0.49
     deh
    0.49
    POSITIVE LOGITS
     automaker
    0.86
     controversial
    0.72
     latest
    0.69
     duo
    0.68
     automakers
    0.68
     revamped
    0.67
     sprawling
    0.65
     brainchild
    0.65
     company
    0.64
     centerpiece
    0.63
    Act Density 0.130%

    No Known Activations