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

    Neuronpedia

    INDEX
    Explanations

    product categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    requent
    0.42
    imental
    0.39
    inental
    0.39
     godfather
    0.38
     etwa
    0.37
    ured
    0.37
    rt
    0.37
    ließ
    0.37
    ridor
    0.36
     isn
    0.36
    POSITIVE LOGITS
     tournaments
    0.40
    𝕀
    0.38
     MgO
    0.37
    cmml
    0.37
     MILLER
    0.37
     FileInputStream
    0.36
     Period
    0.36
     Earthquake
    0.35
    ﺗ
    0.35
     PERIOD
    0.35
    Act Density 0.000%

    No Known Activations