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

    Neuronpedia

    INDEX
    Explanations

    mathematical research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __/
    -0.07
    .Prop
    -0.06
    Px
    -0.06
     Mood
    -0.06
    もの
    -0.06
    つぶ
    -0.06
     -/↵
    -0.06
    .Trans
    -0.06
    .xaxis
    -0.06
    μέν
    -0.06
    POSITIVE LOGITS
     Harmon
    0.07
    ICIENT
    0.07
    erton
    0.06
    pan
    0.06
     Drew
    0.06
    τέρα
    0.06
     Gig
    0.06
     그림
    0.06
     hovered
    0.06
    orth
    0.06
    Act Density 0.016%

    No Known Activations