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

    Neuronpedia

    INDEX
    Explanations

    solitary symptom myself down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wood
    0.41
     literacy
    0.38
     Investment
    0.38
     Memo
    0.38
    ዟ
    0.38
    gling
    0.37
    memo
    0.37
     इजीली
    0.37
    Ruby
    0.37
     impossibility
    0.37
    POSITIVE LOGITS
     σει
    0.42
     Dwarf
    0.42
     δὲ
    0.41
    㚅
    0.40
     dw
    0.40
    DW
    0.39
     dwelt
    0.39
     dwells
    0.39
     dwell
    0.39
     dwarves
    0.39
    Act Density 0.000%

    No Known Activations