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

    Neuronpedia

    INDEX
    Explanations

    Arabic letters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Letters, numbers, or symbols

    np_acts-logits-general · gemini-2.0-flash

    U.S. Aflibercept n+

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.54
     $_"
    -0.53
    RunAsync
    -0.53
    ?».
    -0.53
     Mercurio
    -0.51
    الدراسه
    -0.51
     Silverstone
    -0.50
     Però
    -0.50
     centen
    -0.50
     rosario
    -0.49
    POSITIVE LOGITS
     اين
    0.63
    اي
    0.59
     براي
    0.54
    PMailer
    0.52
    هاي
    0.51
     ك
    0.51
     كه
    0.51
     لينك
    0.50
    اين
    0.50
    يكي
    0.50
    Act Density 0.005%

    No Known Activations