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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miserable
    -0.08
     babies
    -0.07
     Emit
    -0.07
    apply
    -0.06
    |--
    -0.06
     Deniz
    -0.06
     setObject
    -0.06
    .Minimum
    -0.06
    Chicken
    -0.06
     Een
    -0.06
    POSITIVE LOGITS
    pdb
    0.06
    .rdf
    0.06
    fragment
    0.06
    /db
    0.06
    Cert
    0.06
    132
    0.06
    Њ
    0.06
    ители
    0.06
     Vulkan
    0.06
    ráž
    0.06
    Act Density 0.013%

    No Known Activations