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

    Neuronpedia

    INDEX
    Explanations

    brewing profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clogged
    0.50
    я
    0.50
     camp
    0.48
     lineHeight
    0.48
    າຍ
    0.48
    し
    0.46
     campionato
    0.45
     capitalise
    0.45
    રે
    0.45
     confuse
    0.45
    POSITIVE LOGITS
     aides
    0.60
    inescence
    0.53
     aids
    0.51
     Switches
    0.49
     apro
    0.47
    ules
    0.47
    umble
    0.46
     elektrol
    0.46
    ὃ
    0.46
    ções
    0.45
    Act Density 0.000%

    No Known Activations