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

    Neuronpedia

    INDEX
    Explanations

    online platforms and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     магистра
    0.43
     .(
    0.42
    embra
    0.41
     (),
    0.40
     ()
    0.39
    GRESS
    0.39
    брь
    0.39
    ické
    0.39
    }}}+\
    0.39
    ᄈ
    0.38
    POSITIVE LOGITS
     twitter
    0.41
     rejoined
    0.38
     online
    0.38
    stas
    0.38
     http
    0.38
     passphrase
    0.37
     amazon
    0.37
    回家
    0.37
    homepage
    0.36
     rejoin
    0.36
    Act Density 0.000%

    No Known Activations