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

    Neuronpedia

    INDEX
    Explanations

    Code header inclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تعالى
    -0.08
    ﻳ
    -0.07
    .IsChecked
    -0.07
    _regs
    -0.07
    נון
    -0.07
     Farmer
    -0.07
    螨
    -0.07
    _fd
    -0.07
    >#
    -0.07
    _insn
    -0.07
    POSITIVE LOGITS
    )^
    0.07
     src
    0.07
     Fix
    0.07
    тверд
    0.06
    Unit
    0.06
    뵙
    0.06
     prepare
    0.06
     alpha
    0.06
    data
    0.06
     training
    0.06
    Act Density 0.002%

    No Known Activations