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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ائه
    -0.08
    ())[
    -0.08
     nahi
    -0.08
     Pets
    -0.08
    مش
    -0.07
     Glenn
    -0.07
    对象
    -0.07
     Usu
    -0.07
     estat
    -0.07
     Prot
    -0.07
    POSITIVE LOGITS
    0.08
    self
    0.08
     �
    0.07
     †
    0.07
    .ID
    0.07
    eeper
    0.07
    .Linked
    0.07
    ['_
    0.07
    .Hash
    0.07
    �
    0.07
    Act Density 0.170%
    No Known Activations