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

    Neuronpedia

    INDEX
    Explanations

    assigning values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bandages
    0.53
     swamps
    0.51
     aberrations
    0.51
    ,
    0.51
     diaries
    0.49
     ligands
    0.48
     treks
    0.47
     kinases
    0.47
     phonons
    0.46
     walks
    0.46
    POSITIVE LOGITS
    И
    0.55
    none
    0.49
    お
    0.49
    م
    0.48
     хотели
    0.47
    ش
    0.47
    มี
    0.47
    Это
    0.46
    이
    0.46
    dropdown
    0.45
    Act Density 0.014%

    No Known Activations