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

    Neuronpedia

    INDEX
    Explanations

    references to micro-scale phenomena or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with micro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.58
     GenerationType
    -0.56
     mármol
    -0.54
    Fordítás
    -0.53
     saveiro
    -0.53
    IsMutable
    -0.53
     plomo
    -0.53
     navideños
    -0.52
     desmotivaciones
    -0.51
     queſta
    -0.51
    POSITIVE LOGITS
     Micro
    0.93
    Micro
    0.83
     micro
    0.82
     MICRO
    0.65
    micro
    0.62
    MICRO
    0.55
     微
    0.52
     Macro
    0.50
     Mike
    0.47
     Mikro
    0.45
    Act Density 0.028%

    No Known Activations