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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Zur
    -0.08
     Kelley
    -0.08
    ផ្ស
    -0.07
    ，说
    -0.07
    GRE
    -0.07
     Haas
    -0.07
     дэ
    -0.07
     zing
    -0.07
    Aligned
    -0.07
     Wheeler
    -0.07
    POSITIVE LOGITS
     stad
    0.08
    iend
    0.08
    emet
    0.07
    --------------------------------------------------------------------------↵
    0.07
     Latino
    0.07
     termination
    0.07
    タ
    0.07
    ou
    0.07
    end
    0.07
    综合
    0.07
    Act Density 0.001%

    No Known Activations