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

    Neuronpedia

    INDEX
    Explanations

    is a/an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    וה
    0.54
    ו
    0.53
    ERO
    0.52
    Inher
    0.50
     Pico
    0.50
    Execution
    0.49
    Bench
    0.48
    Monitor
    0.48
    ÉT
    0.48
    Conver
    0.47
    POSITIVE LOGITS
     to
    0.52
     endl
    0.48
     nieces
    0.48
     scheduled
    0.47
     piè
    0.46
     approximates
    0.46
     biscuits
    0.45
     alleges
    0.45
     vinyl
    0.45
     legitimate
    0.44
    Act Density 0.002%

    No Known Activations