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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oyo
    -0.06
    \ORM
    -0.06
    ;"↵
    -0.06
    ais
    -0.06
     iz
    -0.06
    افظ
    -0.06
     môi
    -0.06
    ético
    -0.06
    雅
    -0.06
     Walker
    -0.06
    POSITIVE LOGITS
    Jon
    0.07
    _sep
    0.06
    subsection
    0.06
    perator
    0.06
     coral
    0.06
     mono
    0.06
     Poly
    0.06
     olmam
    0.06
    )
↵
    0.06
    Apple
    0.06
    Act Density 0.000%

    No Known Activations