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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provocative
    -0.07
    уються
    -0.06
     فر
    -0.06
     thoughtful
    -0.06
     numberOf
    -0.06
    -Al
    -0.06
     Means
    -0.06
    _LEN
    -0.06
    /sign
    -0.06
     Currently
    -0.06
    POSITIVE LOGITS
     آ
    0.07
    оном
    0.06
     leven
    0.06
    ();?>
    0.06
    .addSubview
    0.06
     amusing
    0.06
    -widget
    0.06
     Capitals
    0.06
    shaft
    0.06
     roy
    0.06
    Act Density 0.032%

    No Known Activations