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

    Neuronpedia

    INDEX
    Explanations

    Location Decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FlashValue
    0.43
    对抗
    0.40
    握
    0.38
     últimas
    0.38
    carboxylate
    0.38
    గొ
    0.36
    ሎጂ
    0.36
    密码
    0.36
    定的
    0.36
    椅子
    0.36
    POSITIVE LOGITS
    tnie
    0.42
     starring
    0.39
     Nú
    0.39
     le
    0.39
     issuing
    0.39
     differently
    0.38
     dort
    0.38
    小さ
    0.38
                        
    0.38
     Viel
    0.37
    Act Density 0.001%

    No Known Activations