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

    Neuronpedia

    INDEX
    Explanations

    L starters and LFS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ским
    0.39
    有问题
    0.37
    \":\"
    0.36
     শরীরের
    0.36
    らく
    0.34
    \:
    0.34
     ছবি
    0.34
    োভ
    0.34
    ᵕ
    0.34
     জীবনের
    0.34
    POSITIVE LOGITS
     L
    0.50
     LC
    0.48
     LIC
    0.46
     LA
    0.45
     लकार
    0.44
     La
    0.44
     Let
    0.44
     LH
    0.43
     LM
    0.42
     LCA
    0.42
    Act Density 0.192%

    No Known Activations