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

    Neuronpedia

    INDEX
    Explanations

    cycles and journey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Running
    0.40
    🦉
    0.38
     అయ్య
    0.37
     Imaging
    0.37
    乏
    0.37
     Information
    0.36
    CSA
    0.36
     Arlington
    0.36
     edits
    0.36
     Silent
    0.36
    POSITIVE LOGITS
     ದೇಹ
    0.42
     prati
    0.39
     Ấ
    0.39
    abic
    0.39
     جسم
    0.38
    亾
    0.38
     لنک
    0.37
     inmig
    0.36
    िन
    0.36
    福祉
    0.36
    Act Density 0.000%

    No Known Activations