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

    Neuronpedia

    INDEX
    Explanations

    heavy, particularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ata
    0.45
    ophobic
    0.44
     scompar
    0.44
     discovers
    0.42
    cse
    0.42
    az
    0.42
    ali
    0.42
     सहित
    0.41
    izioni
    0.41
     Mag
    0.40
    POSITIVE LOGITS
    ल
    0.54
     electrification
    0.53
     at
    0.52
     entreprise
    0.51
     permanente
    0.50
    م
    0.49
     perusahaan
    0.49
    Skippable
    0.47
     electrop
    0.47
     específico
    0.47
    Act Density 0.000%

    No Known Activations