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

    Neuronpedia

    INDEX
    Explanations

    bottles and cans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tc
    -0.07
     Elaine
    -0.07
     Swamp
    -0.06
     Tantra
    -0.06
    гот
    -0.06
     đào
    -0.06
    فال
    -0.06
     Hành
    -0.06
    ariance
    -0.06
    .MustCompile
    -0.06
    POSITIVE LOGITS
     repairs
    0.08
     discipl
    0.07
    returns
    0.06
     OMG
    0.06
     arist
    0.06
     module
    0.06
     permissions
    0.06
     inspire
    0.06
    ريط
    0.06
    [this
    0.06
    Act Density 0.009%

    No Known Activations