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

    Neuronpedia

    INDEX
    Explanations

    league of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hol
    0.45
    t
    0.45
    r
    0.43
    hy
    0.42
    zz
    0.42
    lith
    0.41
    Watts
    0.40
    лич
    0.40
    hiya
    0.40
     হে
    0.39
    POSITIVE LOGITS
     табли
    0.59
     лига
    0.52
     Лига
    0.52
     ligands
    0.52
     leagues
    0.52
    Lig
    0.52
     Liga
    0.51
     ligand
    0.51
     liga
    0.50
     Lig
    0.48
    Act Density 0.003%

    No Known Activations