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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obtiene
    -0.09
     हिस
    -0.08
     blom
    -0.08
     வளர
    -0.08
     பெற
    -0.08
     pendent
    -0.07
     прие
    -0.07
     rsp
    -0.07
     pener
    -0.07
     قائم
    -0.07
    POSITIVE LOGITS
    意思
    0.10
     বাক
    0.09
     sentence
    0.09
     सूचना
    0.08
     Sentence
    0.08
    sentence
    0.08
     Aussage
    0.08
    Sentence
    0.08
     implies
    0.08
    什么意思
    0.08
    Act Density 0.205%

    No Known Activations