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

    Neuronpedia

    INDEX
    Explanations

    names after titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     macroeconomic
    0.90
     correlated
    0.83
    🤲
    0.80
     comparable
    0.80
     substantially
    0.78
    😧
    0.77
     interpre
    0.76
    avacanam
    0.75
     tuberculosis
    0.75
     columnar
    0.75
    POSITIVE LOGITS
    Dude
    1.03
    Noir
    1.02
    Z
    0.98
    Dark
    0.98
    Tech
    0.94
    Alpha
    0.92
    Rock
    0.91
    Fly
    0.90
    Zombie
    0.90
    Rusty
    0.90
    Act Density 0.378%

    No Known Activations