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

    Neuronpedia

    INDEX
    Explanations

    dust, rain, gold, thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibr
    0.44
     VPN
    0.42
     handkerchief
    0.42
     builder
    0.41
    lığı
    0.41
     antiga
    0.40
    }}+\
    0.39
    hyper
    0.39
     poodle
    0.39
     ເ
    0.39
    POSITIVE LOGITS
     Completed
    0.50
     Anwendungen
    0.46
    ERT
    0.45
    мо
    0.45
    どんな
    0.45
    恫
    0.45
    unning
    0.44
    mot
    0.43
    Б
    0.43
     rechnen
    0.42
    Act Density 0.000%

    No Known Activations