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

    Neuronpedia

    INDEX
    Explanations

    General statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Today
    -0.07
    Λ
    -0.07
    templates
    -0.06
    を開
    -0.06
    allocator
    -0.06
    .sel
    -0.06
    roids
    -0.06
     warfare
    -0.06
     spect
    -0.06
    	random
    -0.06
    POSITIVE LOGITS
     승
    0.06
     directories
    0.06
     پیدا
    0.06
     implic
    0.06
    姊
    0.06
    (Screen
    0.06
     backgroundImage
    0.06
     cyc
    0.06
     john
    0.06
    bits
    0.06
    Act Density 0.050%

    No Known Activations