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

    Neuronpedia

    INDEX
    Explanations

    lm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vamp
    -0.07
     Ran
    -0.06
    Standing
    -0.06
     Pakistani
    -0.06
     INSERT
    -0.06
    .is
    -0.06
    ’hui
    -0.06
    --[[
    -0.06
     absentee
    -0.06
    Ü
    -0.06
    POSITIVE LOGITS
    LM
    0.31
    lm
    0.18
     LM
    0.07
    рим
    0.07
    ilm
    0.07
     MLM
    0.07
    atisf
    0.06
    ilim
    0.06
     jm
    0.06
     reclaim
    0.06
    Act Density 0.002%

    No Known Activations