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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sound
    -0.07
    woord
    -0.07
    matter
    -0.07
    Go
    -0.07
    fun
    -0.07
     ![
    -0.06
     Je
    -0.06
     fileId
    -0.06
     wool
    -0.06
     bursts
    -0.06
    POSITIVE LOGITS
    ALS
    0.08
     höchst
    0.07
    .Max
    0.07
     함
    0.07
     fragile
    0.07
    ocaly
    0.07
     주장
    0.07
     dealings
    0.07
    แด
    0.07
    �
    0.07
    Act Density 0.002%

    No Known Activations