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

    Neuronpedia

    INDEX
    Explanations

    Dimensions and Units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .WRAP
    -0.06
    із
    -0.06
     spat
    -0.06
    уков
    -0.06
     Newly
    -0.06
     cunning
    -0.06
     cloak
    -0.06
    　　　　　　　　　
    -0.06
     Gy
    -0.05
     recep
    -0.05
    POSITIVE LOGITS
    308
    0.07
    :{
↵
    0.06
    μερ
    0.06
     intl
    0.06
    IEnumerable
    0.06
    격
    0.06
    linkplain
    0.06
    ็บ
    0.06
     ConfigurationManager
    0.06
    _MEDIA
    0.06
    Act Density 0.005%

    No Known Activations