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

    Neuronpedia

    INDEX
    Explanations

    unique, out-of-context words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acks
    -1.06
     Singleton
    -0.84
    Singleton
    -0.71
    o
    -0.55
    ACKS
    -0.51
     Mecca
    -0.48
     singleton
    -0.47
    i
    -0.44
    ed
    -0.42
    Портал
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.92
     lenker
    0.89
     ujednoznacz
    0.87
     Italijanski
    0.84
    0.82
     estimés
    0.78
    FormBuilder
    0.75
     Forder
    0.75
    NOPQRST
    0.74
    GHIJKLM
    0.73
    Act Density 0.871%

    No Known Activations