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

    Neuronpedia

    INDEX
    Explanations

    going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     акчага
    0.45
    ্ে
    0.41
    点が
    0.40
    BLINK
    0.38
    (("
    0.37
    spacer
    0.36
     cyclospor
    0.36
    接收
    0.36
    dincer
    0.36
     methylene
    0.36
    POSITIVE LOGITS
     Going
    0.57
    ToBe
    0.50
     Strong
    0.48
     going
    0.48
    Going
    0.47
    going
    0.41
    Strong
    0.41
     mạnh
    0.41
    リー
    0.39
     Platforms
    0.38
    Act Density 0.004%

    No Known Activations