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

    Neuronpedia

    INDEX
    Explanations

    Material expansion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tempered
    -0.07
    の方
    -0.06
    觇
    -0.06
     similarly
    -0.06
     implants
    -0.06
     '../
    -0.06
     mô
    -0.06
     adec
    -0.06
    具体的
    -0.06
     btw
    -0.06
    POSITIVE LOGITS
     Lamb
    0.08
    굶
    0.07
     PERMISSION
    0.07
    嘣
    0.07
    gebung
    0.07
    )NSString
    0.07
    Destroyed
    0.07
     région
    0.07
    Jean
    0.07
    𨱔
    0.07
    Act Density 0.063%

    No Known Activations