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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ceptor
    -0.07
    �ng
    -0.07
    layan
    -0.06
    _none
    -0.06
    .substring
    -0.06
     measurement
    -0.06
     sadly
    -0.06
    zą
    -0.06
     яку
    -0.06
    ικών
    -0.06
    POSITIVE LOGITS
     representative
    0.06
     Throws
    0.06
    -load
    0.06
     amused
    0.06
     brute
    0.06
     subscribers
    0.06
    elligent
    0.06
    DECREF
    0.06
     Portal
    0.06
     Oculus
    0.06
    Act Density 0.011%

    No Known Activations