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

    Neuronpedia

    INDEX
    Explanations

    own or other's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Correspond
    0.37
    onti
    0.37
    到一个
    0.36
    Rainbow
    0.36
    デ
    0.36
     スマ
    0.36
     horizontale
    0.36
    Parad
    0.35
    でしょうか
    0.35
    ટક
    0.35
    POSITIVE LOGITS
     theirs
    1.61
     hers
    1.58
     yours
    1.53
     ours
    1.49
     Yours
    1.35
    Yours
    1.31
     mine
    1.23
     Ours
    1.18
     own
    1.16
     Own
    1.08
    Act Density 0.020%

    No Known Activations