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

    Neuronpedia

    INDEX
    Explanations

    queries for latest information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒍
    3.79
    𝒊
    3.44
    𝒓
    3.20
     HomeComponent
    3.14
     stagger
    3.08
    𝒔
    3.06
     certiorari
    2.99
    ного
    2.99
    𝒐
    2.96
    assertThat
    2.90
    POSITIVE LOGITS
    d
    4.02
    берите
    3.17
    त
    3.13
    sia
    3.04
    s
    2.94
    heid
    2.87
    किस्तान
    2.70
    c
    2.61
    g
    2.61
    न
    2.61
    Act Density 0.011%

    No Known Activations