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

    Neuronpedia

    INDEX
    Explanations

    brackets and parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ynos
    -0.07
    _PREVIEW
    -0.07
    教授
    -0.07
     доме
    -0.07
     xrange
    -0.06
     právě
    -0.06
     Trung
    -0.06
    Born
    -0.06
    _resp
    -0.06
    _above
    -0.06
    POSITIVE LOGITS
    enan
    0.07
     Target
    0.07
    출
    0.06
    Ca
    0.06
    šek
    0.06
    SENS
    0.06
     barriers
    0.06
     MA
    0.06
     unlocks
    0.06
    esis
    0.06
    Act Density 0.026%

    No Known Activations