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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نکرد
    -0.09
     Peacock
    -0.08
     નથી
    -0.08
     Provider
    -0.08
     unidentified
    -0.08
    prache
    -0.07
     unaware
    -0.07
    away
    -0.07
     забуд
    -0.07
    acia
    -0.07
    POSITIVE LOGITS
     nevertheless
    0.09
     nonetheless
    0.09
    Nevertheless
    0.09
     valuable
    0.08
     Appalach
    0.08
    켓
    0.08
     invaluable
    0.08
    Such
    0.08
    值得
    0.08
     certainly
    0.07
    Act Density 0.028%

    No Known Activations