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

    Neuronpedia

    INDEX
    Explanations

    words related to technical documentation, especially within scientific or engineering contexts.

    oai_token-act-pair · gemini-2.0-flash

    mask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.71
     AssemblyCompany
    -0.64
     lits
    -0.58
     dis
    -0.56
     MotionEvent
    -0.54
     المعيارى
    -0.52
    XPATH
    -0.52
    Atoi
    -0.52
    اهش
    -0.51
    ISPR
    -0.51
    POSITIVE LOGITS
    oredCriteria
    0.51
     stället
    0.51
     Malabar
    0.51
    ⓧ
    0.49
     förstå
    0.49
     forbindelse
    0.48
     yourselves
    0.48
     arbej
    0.47
     împre
    0.46
     prová
    0.46
    Act Density 5.540%

    No Known Activations