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

    Neuronpedia

    INDEX
    Explanations

    Same color probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Inner
    -0.07
     indy
    -0.07
    indo
    -0.07
    ationship
    -0.07
    Associate
    -0.07
    asus
    -0.07
     discusses
    -0.07
     이
    -0.07
    iraan
    -0.07
    ibase
    -0.07
    POSITIVE LOGITS
     पूरी
    0.09
     gangen
    0.09
    /an
    0.08
     uninterrupted
    0.08
     separated
    0.08
     separation
    0.08
     enten
    0.08
    either
    0.08
     entweder
    0.08
     Either
    0.07
    Act Density 0.032%

    No Known Activations