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

    Neuronpedia

    INDEX
    Explanations

    -family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .books
    -0.07
    .sul
    -0.06
    ',(
    -0.06
    τρα
    -0.06
     dwind
    -0.06
    _Back
    -0.06
     Sussex
    -0.06
    VAS
    -0.06
     walkers
    -0.06
     sworn
    -0.06
    POSITIVE LOGITS
    EMPLATE
    0.07
     kitchen
    0.06
    ynomials
    0.06
     gambling
    0.06
     OMG
    0.06
    Iter
    0.06
    暗
    0.06
    .repo
    0.06
     منتشر
    0.06
    gone
    0.06
    Act Density 0.000%

    No Known Activations