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

    Neuronpedia

    INDEX
    Explanations

    concepts and clarifying questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.52
     at
    0.47
     mobile
    0.46
    (
    0.45
     unlocked
    0.45
     capped
    0.44
     tracked
    0.44
     >
    0.44
    昆
    0.44
     checkboxes
    0.43
    POSITIVE LOGITS
     Gölü
    0.56
     Gül
    0.53
    ๗
    0.52
    雎
    0.52
     Energía
    0.50
     Jego
    0.49
    pflege
    0.49
    原始内容
    0.49
     Deja
    0.48
     duelo
    0.47
    Act Density 0.003%

    No Known Activations