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

    Neuronpedia

    INDEX
    Explanations

    describes properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sized
    -0.91
     reaction
    -0.88
    reaction
    -0.85
     Reaction
    -0.79
    Reaction
    -0.79
     shaped
    -0.72
     REACTION
    -0.67
    shaped
    -0.66
     Shaped
    -0.66
    sized
    -0.66
    POSITIVE LOGITS
     Reverso
    0.79
    +#+#
    0.70
    IVEREF
    0.68
     للاسماء
    0.68
    Vidite
    0.68
     EconPapers
    0.67
    #+#
    0.67
    writeField
    0.66
    AutoScaleMode
    0.65
     kaarangay
    0.63
    Act Density 0.040%

    No Known Activations