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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clandestine
    0.51
     desenvolved
    0.50
     NuGet
    0.49
     Diarsipkan
    0.49
     clandest
    0.48
     EBITDA
    0.47
     bygone
    0.47
     Rolex
    0.46
     Forschungs
    0.46
     bewild
    0.46
    POSITIVE LOGITS
    oa
    0.52
    uc
    0.46
    L
    0.44
    ua
    0.44
    if
    0.43
    ust
    0.43
    tag
    0.43
    2
    0.42
    return
    0.41
    ien
    0.41
    Act Density 0.248%

    No Known Activations