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

    Neuronpedia

    INDEX
    Explanations

    classic for a reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бана
    0.49
     пусто
    0.46
    Roth
    0.45
    Gone
    0.45
    Mess
    0.44
     Kef
    0.43
    ீர்கள்
    0.42
     dinâmica
    0.42
     decyz
    0.42
    淦
    0.42
    POSITIVE LOGITS
     proportion
    0.49
     Proportion
    0.47
     products
    0.47
     প্রদেশের
    0.47
     contracted
    0.45
     kinds
    0.44
     Products
    0.44
     proportional
    0.44
     कह
    0.44
    ivatives
    0.43
    Act Density 0.006%

    No Known Activations