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

    Neuronpedia

    INDEX
    Explanations

    code/file types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ries
    -1.41
    RIES
    -1.03
    μβρίου
    -0.66
     Ried
    -0.66
    RIED
    -0.61
    GrantedAuthority
    -0.61
    ires
    -0.60
    mals
    -0.60
    wives
    -0.60
     rie
    -0.59
    POSITIVE LOGITS
    ьаж
    0.50
     MutableLiveData
    0.48
    __*/
    0.48
     kaarangay
    0.47
    SharedCtor
    0.47
     protoimpl
    0.46
    ArrowToggle
    0.46
    ఔ
    0.45
     Kers
    0.44
    ValueStyle
    0.43
    Act Density 0.012%

    No Known Activations