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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.49
     beteken
    -0.45
    StateException
    -0.45
    complexContent
    -0.45
     interactions
    -0.45
     interaction
    -0.43
    mited
    -0.42
     Laine
    -0.41
    ccoli
    -0.40
     wireType
    -0.40
    POSITIVE LOGITS
     admins
    0.73
    WriteBarrier
    0.73
     travellers
    0.72
     breeders
    0.71
    AndEndTag
    0.70
     tourists
    0.70
     administrators
    0.69
     adults
    0.68
    Directors
    0.67
     siblings
    0.67
    Act Density 0.005%

    No Known Activations