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

    Neuronpedia

    INDEX
    Explanations

    unlike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    єн
    0.44
     แถม
    0.42
    akova
    0.40
    兟
    0.40
     अभिभाव
    0.40
     pourront
    0.39
     гражда
    0.39
    只会
    0.39
     सम्मान
    0.39
     pourra
    0.39
    POSITIVE LOGITS
     unlike
    0.62
     Unlike
    0.57
     often
    0.52
     emphasises
    0.51
     characteristic
    0.50
    வதில்லை
    0.48
     almost
    0.46
     emphasise
    0.46
     sometimes
    0.46
    Unlike
    0.46
    Act Density 0.078%

    No Known Activations