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

    Neuronpedia

    INDEX
    Explanations

    numbers and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ാരോഗ്യ
    0.22
    Trajectories
    0.22
    Sprites
    0.22
    ableConcept
    0.21
    澼
    0.21
    腧
    0.21
    Celltype
    0.21
    CCCc
    0.21
    jasama
    0.21
    迪士
    0.21
    POSITIVE LOGITS
    ↵
    0.31
    5
    0.29
    ↵↵
    0.28
    7
    0.25
     for
    0.25
    8
    0.25
    4
    0.25
     was
    0.24
    9
    0.24
    6
    0.24
    Act Density 0.302%

    No Known Activations