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

    Neuronpedia

    INDEX
    Explanations

    sudo commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ac
    0.67
    aks
    0.61
    eks
    0.61
    ünk
    0.59
    ec
    0.58
    EC
    0.58
     FC
    0.58
    ak
    0.57
    Sek
    0.55
     EC
    0.55
    POSITIVE LOGITS
     Gri
    1.24
     Stra
    1.14
     Ramb
    1.14
    ravi
    1.14
    aloo
    1.13
    Gri
    1.13
     Navi
    1.13
     Viola
    1.12
     Wadi
    1.10
     CIV
    1.08
    Act Density 0.371%

    No Known Activations