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
     transforms
    -0.08
    .ch
    -0.07
     deliveries
    -0.07
    <Component
    -0.07
    Kids
    -0.07
    _commands
    -0.07
    leaf
    -0.07
    amespace
    -0.07
    (arguments
    -0.07
    ensaje
    -0.07
    POSITIVE LOGITS
    붉
    0.07
    흗
    0.07
    当地的
    0.07
    ᄄ
    0.07
    핳
    0.07
    גישה
    0.07
     Sheridan
    0.07
     tán
    0.07
     noting
    0.07
    �
    0.07
    Act Density 0.010%

    No Known Activations