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

    Neuronpedia

    INDEX
    Explanations

    memory storage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.84
     myſelf
    -0.80
     Monfieur
    -0.77
    出版年
    -0.76
    enumi
    -0.75
     Theſe
    -0.75
    Personendaten
    -0.74
     Anſ
    -0.73
     whoſe
    -0.73
     Eſ
    -0.71
    POSITIVE LOGITS
    Ecotoxicity
    0.55
     radio
    0.52
     progress
    0.48
     entre
    0.48
    rawDesc
    0.46
     qu
    0.46
     Radio
    0.46
     Pol
    0.45
     pro
    0.45
    葩
    0.45
    Act Density 0.047%

    No Known Activations