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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate reasoning steps in problem-solving.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obierno
    -0.06
    .scalablytyped
    -0.06
    odule
    -0.06
    IFn
    -0.06
    nda
    -0.06
    ijn
    -0.06
    GINE
    -0.06
    abbo
    -0.06
    oscope
    -0.06
    :normal
    -0.06
    POSITIVE LOGITS
    à¸ģรรมà¸ģาร
    0.08
     both
    0.07
     varying
    0.07
    utton
    0.06
     wherever
    0.06
     each
    0.06
    both
    0.06
    ëħ
    0.06
    asil
    0.06
     Prest
    0.06
    Act Density 0.143%

    No Known Activations