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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istry
    -0.06
    ウェ
    -0.06
     چند
    -0.06
     unborn
    -0.06
     dangerously
    -0.06
     Kindle
    -0.06
     prohib
    -0.06
    Way
    -0.06
     Kü
    -0.06
     yok
    -0.06
    POSITIVE LOGITS
    _ALIGN
    0.07
    -caption
    0.06
    .IsEmpty
    0.06
    �
    0.06
        ↵↵
    0.06
     chute
    0.06
     Engineer
    0.06
     بالرياض
    0.06
    .AppCompatActivity
    0.06
     Training
    0.06
    Act Density 0.118%

    No Known Activations