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

    Neuronpedia

    INDEX
    Explanations

    North, South, directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    睬
    0.45
     প্রতিশোধ
    0.37
    Probit
    0.36
    たた
    0.36
    धाना
    0.35
    GaussianBlur
    0.35
    හාර
    0.35
     pushedAt
    0.35
    getPrice
    0.35
    ဵ
    0.35
    POSITIVE LOGITS
     N
    1.06
     north
    1.05
     east
    0.91
     west
    0.89
    north
    0.88
     northwest
    0.88
     شمال
    0.86
     south
    0.82
    N
    0.82
     NW
    0.82
    Act Density 0.010%

    No Known Activations