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

    Neuronpedia

    INDEX
    Explanations

    json object keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Insol
    1.29
     Fatt
    1.28
     Poste
    1.24
     Spend
    1.22
     Priv
    1.21
     Tribut
    1.20
     Bonnet
    1.20
     Minor
    1.19
     Dat
    1.19
     Oficina
    1.19
    POSITIVE LOGITS
     blast
    1.19
    blasts
    1.16
     blasts
    1.10
     bullets
    1.09
    leted
    1.07
    নির্ম
    1.07
    buster
    1.06
     αί
    1.04
    驳
    1.03
    lets
    1.02
    Act Density 0.001%

    No Known Activations