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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     funct
    -0.07
     sonraki
    -0.07
    SCRIPTION
    -0.07
     dolay
    -0.07
     nurture
    -0.07
    arent
    -0.06
    िल
    -0.06
    ıkl
    -0.06
    ین
    -0.06
    .Make
    -0.06
    POSITIVE LOGITS
    (effect
    0.07
    _bh
    0.07
    ्ग
    0.06
    ичні
    0.06
     popul
    0.06
     interns
    0.06
    _symbols
    0.06
     struggling
    0.06
    -review
    0.06
    Portfolio
    0.06
    Act Density 0.001%

    No Known Activations