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

    Neuronpedia

    INDEX
    Explanations

    ))

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桐
    -0.07
    AndUpdate
    -0.07
    Γ
    -0.06
     hete
    -0.06
    ombok
    -0.06
     Girls
    -0.06
    GBP
    -0.06
    Study
    -0.06
    	center
    -0.06
     оттен
    -0.06
    POSITIVE LOGITS
    IBILITY
    0.08
    classification
    0.07
    .Rem
    0.06
    getSingleton
    0.06
    =R
    0.06
     grids
    0.06
     AuthenticationService
    0.06
    �
    0.06
     ImmutableList
    0.06
    ics
    0.06
    Act Density 0.000%

    No Known Activations