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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bat
    -0.07
     currency
    -0.07
    ват
    -0.07
     tty
    -0.06
    (video
    -0.06
    .consumer
    -0.06
     chaotic
    -0.06
     История
    -0.06
    interp
    -0.06
    (interp
    -0.06
    POSITIVE LOGITS
    ěst
    0.08
    ersed
    0.07
     sia
    0.06
    evento
    0.06
    attendance
    0.06
     thoughtful
    0.06
    raising
    0.06
    reh
    0.06
    eydi
    0.06
    leo
    0.06
    Act Density 0.067%

    No Known Activations