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

    Neuronpedia

    INDEX
    Explanations

    Essentially

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Essentially
    -0.95
    essentially
    -0.88
    Essentially
    -0.82
     essentially
    -0.78
     Efq
    -0.75
     Theſe
    -0.75
     Majefty
    -0.73
     Jefus
    -0.65
     poffible
    -0.65
     questionable
    -0.64
    POSITIVE LOGITS
    nosaurus
    0.55
    NameInMap
    0.54
    ussis
    0.50
    पया
    0.48
    ngilizce
    0.46
    смотра
    0.44
    rungsseite
    0.44
    isers
    0.44
    白石
    0.44
     sekali
    0.43
    Act Density 0.194%

    No Known Activations