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

    Neuronpedia

    INDEX
    Explanations

    consider

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umann
    -0.08
    цию
    -0.08
     topology
    -0.08
     perform
    -0.08
    CRM
    -0.07
    Surface
    -0.07
    ᵏ
    -0.07
    mu
    -0.07
    未知
    -0.07
     schl
    -0.07
    POSITIVE LOGITS
     disclosures
    0.07
    getFile
    0.07
     предоставля
    0.07
    专项资金
    0.07
     understandably
    0.07
     Booker
    0.07
     chooser
    0.07
    Feels
    0.07
    Slots
    0.06
     whims
    0.06
    Act Density 0.024%

    No Known Activations