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

    Neuronpedia

    INDEX
    Explanations

    runs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soap
    -0.07
     Revel
    -0.07
    TM
    -0.06
    頻
    -0.06
     mountain
    -0.06
    anny
    -0.06
     melting
    -0.06
     weakest
    -0.06
    )t
    -0.06
    dım
    -0.06
    POSITIVE LOGITS
     SPDX
    0.06
    asionally
    0.06
    _admin
    0.06
    (express
    0.06
    _TER
    0.06
    kont
    0.06
    (record
    0.06
    anggan
    0.06
     getPrice
    0.06
     getContext
    0.06
    Act Density 0.097%

    No Known Activations