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

    Neuronpedia

    INDEX
    Explanations

    just say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LAT
    0.44
     جما
    0.42
    rzym
    0.40
     IIT
    0.40
    oucester
    0.39
    pictured
    0.39
     jou
    0.38
    salaryfrom
    0.38
    Coconut
    0.38
    BB
    0.38
    POSITIVE LOGITS
    勝利
    0.54
     Minor
    0.52
    ﮈ
    0.52
     derrot
    0.49
     funções
    0.49
     versiones
    0.49
     Describe
    0.48
     Tennis
    0.48
     curvas
    0.48
     goles
    0.48
    Act Density 0.003%

    No Known Activations