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

    Neuronpedia

    INDEX
    Explanations

    the act of declaring or making a judgement

    oai_token-act-pair · gemini-2.0-flash

    legal decisions/claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     made
    -1.29
    made
    -1.22
     Made
    -1.17
     Making
    -1.16
    Made
    -1.16
     make
    -1.13
    Making
    -1.11
     MADE
    -1.11
     Make
    -1.09
    make
    -1.05
    POSITIVE LOGITS
     endorsements
    0.60
    contentLoaded
    0.57
     bisous
    0.56
    pozdrawiam
    0.56
     Lode
    0.55
     Pasha
    0.54
    winds
    0.54
     rapids
    0.54
     Winds
    0.53
    PerformLayout
    0.53
    Act Density 3.600%

    No Known Activations