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

    Neuronpedia

    INDEX
    Explanations

    Rest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bring
    -0.90
    Bring
    -0.84
     bring
    -0.77
    bring
    -0.64
    +#+
    -0.56
     BRING
    -0.55
     vast
    -0.53
     brings
    -0.48
    Bringing
    -0.48
     IndexPath
    -0.48
    POSITIVE LOGITS
    ness
    0.75
    nesses
    0.71
    ative
    0.67
    ences
    0.66
    rooms
    0.66
    ster
    0.66
    ances
    0.66
    lies
    0.65
    PerformLayout
    0.65
    ing
    0.64
    Act Density 1.592%

    No Known Activations