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

    Neuronpedia

    INDEX
    Explanations

    possessives/contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    often
    -0.06
     Monaco
    -0.06
     �
    -0.06
    ofi
    -0.06
     Tried
    -0.06
    ethoven
    -0.06
     �
    -0.06
    <|start_header_id|>
    -0.06
    plr
    -0.06
    |,↵
    -0.06
    POSITIVE LOGITS
    ’s
    0.07
    's
    0.07
     dessert
    0.06
     embedded
    0.06
    ेग
    0.06
    MD
    0.06
    _SMS
    0.06
    makta
    0.06
     topic
    0.06
     原
    0.06
    Act Density 0.043%

    No Known Activations