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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அந்
    0.64
     sl
    0.60
     widely
    0.60
     correlating
    0.59
     जेल
    0.58
     swimming
    0.58
    див
    0.57
     palm
    0.57
     backpack
    0.57
     backpacks
    0.56
    POSITIVE LOGITS
    (“
    0.80
    }(-\
    0.77
    .(*
    0.77
    ("#
    0.76
    (*
    0.73
     불러
    0.72
     (‘
    0.71
    ('#
    0.70
     フレ
    0.69
    स्पिर
    0.68
    Act Density 0.001%

    No Known Activations