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

    Neuronpedia

    INDEX
    Explanations

    say "osis" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hamilton
    -0.07
     thẳng
    -0.07
     Collins
    -0.07
    abol
    -0.07
    جتماعية
    -0.06
    gü
    -0.06
    hoff
    -0.06
    Motor
    -0.06
    אוניברסיטת
    -0.06
     Gron
    -0.06
    POSITIVE LOGITS
    latin
    0.07
     çeş
    0.07
    玶
    0.07
     seal
    0.07
    Scrollbar
    0.07
     cryptoc
    0.07
     uğra
    0.07
    กำหนด
    0.07
    分割
    0.06
     text
    0.06
    Act Density 0.004%

    No Known Activations