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

    Neuronpedia

    INDEX
    Explanations

    LaTeX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _handlers
    -0.07
    enberg
    -0.07
    ič
    -0.07
    lec
    -0.07
    ux
    -0.07
    िष
    -0.07
    Exclude
    -0.06
    .Dataset
    -0.06
    repair
    -0.06
    iação
    -0.06
    POSITIVE LOGITS
    τές
    0.06
     dek
    0.06
     wishing
    0.06
    最大
    0.06
     consult
    0.06
    kaar
    0.06
     Method
    0.06
    -agent
    0.06
    Scotland
    0.06
     HTMLElement
    0.06
    Act Density 0.021%

    No Known Activations