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

    Neuronpedia

    INDEX
    Explanations

    +/-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stories
    -0.08
     forbidden
    -0.06
     meta
    -0.06
     suiv
    -0.06
     expecting
    -0.06
     iid
    -0.06
     comparing
    -0.06
    793
    -0.06
     ranked
    -0.06
     elapsed
    -0.06
    POSITIVE LOGITS
     apoptosis
    0.07
     ग
    0.06
    喊
    0.06
     Oaks
    0.06
    /stdc
    0.06
     genie
    0.06
    řeb
    0.06
    亲
    0.06
    assandra
    0.06
     letzten
    0.06
    Act Density 0.001%

    No Known Activations