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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _predictions
    -0.07
     Allocation
    -0.07
     allocated
    -0.07
    /Delete
    -0.07
     elkaar
    -0.06
     già
    -0.06
    顔を
    -0.06
     headphones
    -0.06
     fraction
    -0.06
     typedef
    -0.06
    POSITIVE LOGITS
    y
    0.12
    Y
    0.11
    chy
    0.09
    ty
    0.09
    cky
    0.08
     Rocky
    0.08
    سي
    0.08
    ei
    0.08
    appy
    0.08
    .Y
    0.08
    Act Density 0.063%

    No Known Activations