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

    Neuronpedia

    INDEX
    Explanations

    complexities of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝕥
    0.44
    chlor
    0.40
     তৈরি
    0.38
    Pairs
    0.38
     impulsar
    0.38
    ကို
    0.38
    𝗧
    0.38
     Piv
    0.36
    шие
    0.36
     დროს
    0.36
    POSITIVE LOGITS
    ىرى
    0.40
     અન્ય
    0.38
     mình
    0.37
    िडी
    0.37
     समूह
    0.37
    ಬ್ಬ
    0.36
     neighbors
    0.36
     अन्य
    0.36
    ुम
    0.35
     afstand
    0.35
    Act Density 0.001%

    No Known Activations