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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     л
    -0.07
     Apollo
    -0.07
    '=>'
    -0.07
    Topology
    -0.06
    AVIS
    -0.06
    idia
    -0.06
    ulings
    -0.06
     гре
    -0.06
    с
    -0.06
     Glasgow
    -0.06
    POSITIVE LOGITS
     each
    0.10
     every
    0.09
     Each
    0.08
    each
    0.07
    ecz
    0.07
    -any
    0.07
    eci
    0.07
     کودکان
    0.07
    icians
    0.06
     dept
    0.06
    Act Density 0.015%

    No Known Activations