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

    Neuronpedia

    INDEX
    Explanations

    asset servicing decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ystring
    0.44
     lard
    0.40
    iline
    0.39
     pave
    0.39
    rétaire
    0.38
     afterthought
    0.37
     mapping
    0.36
     persistence
    0.36
     paving
    0.36
     decking
    0.36
    POSITIVE LOGITS
    璽
    0.38
    𝐁
    0.38
     пациента
    0.37
    Saf
    0.36
     cuốn
    0.35
     Kontrolle
    0.35
     রোগীর
    0.35
     ministers
    0.35
    選択
    0.35
    ❐
    0.35
    Act Density 0.002%

    No Known Activations