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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and clause introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    čem
    -0.47
     saja
    -0.44
    ulsory
    -0.41
    ”。
    -0.40
    vient
    -0.40
    mely
    -0.39
    epam
    -0.38
    cillor
    -0.38
     extremos
    -0.37
    enerbah
    -0.37
    POSITIVE LOGITS
     myſelf
    1.19
     Theſe
    1.04
     itſelf
    0.99
     raiſ
    0.93
     themſelves
    0.91
     Jefus
    0.91
     chofe
    0.90
     himſelf
    0.89
     fhew
    0.89
     Majefty
    0.89
    Act Density 0.194%

    No Known Activations