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

    Neuronpedia

    INDEX
    Explanations

    Korea and Japan attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佶
    0.75
    骧
    0.74
     LoginPage
    0.72
    屓
    0.71
     Besonders
    0.71
    ங்கிணை
    0.70
     constituent
    0.69
     黒
    0.69
     rhombus
    0.69
    قف
    0.68
    POSITIVE LOGITS
    es
    1.20
    ers
    1.02
    cock
    0.95
    en
    0.91
    on
    0.90
    age
    0.90
    ager
    0.86
    ERS
    0.86
    𝘢
    0.86
    ere
    0.86
    Act Density 0.000%

    No Known Activations