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

    Neuronpedia

    INDEX
    Explanations

    option, alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৬০
    0.44
    Curtis
    0.40
     Deepak
    0.39
     Clarity
    0.39
     ಪ್ರಮಾಣ
    0.39
     চিহ্ন
    0.38
     অ্যাপ্লিকেশন
    0.38
     Rhône
    0.38
     GMC
    0.37
     Helix
    0.36
    POSITIVE LOGITS
    alternative
    0.55
     alternative
    0.54
    ALTERNATIVE
    0.48
    Alternative
    0.48
     unlucky
    0.47
     option
    0.47
     alternatif
    0.47
     альтерна
    0.46
     alternatives
    0.46
     opção
    0.46
    Act Density 0.010%

    No Known Activations