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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    歐
    -0.07
    ...',↵
    -0.07
    observ
    -0.07
    .special
    -0.07
    utting
    -0.07
    avour
    -0.06
     swipe
    -0.06
     wallet
    -0.06
    Population
    -0.06
     neben
    -0.06
    POSITIVE LOGITS
    972
    0.06
    ()=="
    0.06
     Keeps
    0.06
    .drop
    0.06
    /App
    0.06
    δρο
    0.06
     �
    0.06
     aider
    0.05
     �
    0.05
     норматив
    0.05
    Act Density 0.000%

    No Known Activations