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

    Neuronpedia

    INDEX
    Explanations

    six friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Penn
    0.41
    ')}>
    0.40
    眎
    0.39
    मियल
    0.38
     preponder
    0.38
    垍
    0.38
     প্রেসিডেন্ট
    0.37
     reichen
    0.37
    assertThat
    0.36
     Präsident
    0.36
    POSITIVE LOGITS
     Gallery
    0.41
    ROSS
    0.40
     gallery
    0.38
     ditch
    0.37
     Sdn
    0.37
     ROC
    0.36
    Gallery
    0.36
     ทำ
    0.36
     내부
    0.36
    enrich
    0.36
    Act Density 0.000%

    No Known Activations