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

    Neuronpedia

    INDEX
    Explanations

    Math and data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mmmm
    -0.08
     Lincoln
    -0.08
     Св
    -0.07
    Nec
    -0.07
    mp
    -0.07
    Peer
    -0.07
     ಅಥವಾ
    -0.07
    -0.07
     dependency
    -0.07
     influencer
    -0.07
    POSITIVE LOGITS
     alike
    0.11
     Hinsicht
    0.08
     बेह
    0.08
     gleicher
    0.08
     sead
    0.08
     retour
    0.07
     cercle
    0.07
     دونوں
    0.07
    寝
    0.07
     조직
    0.07
    Act Density 0.100%
    No Known Activations