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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or sections within structured documents

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

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
    ſelves
    -0.55
     mauva
    -0.55
     Wikimedijinoj
    -0.55
     Monfieur
    -0.53
    ſelf
    -0.52
    MessageTagHelper
    -0.51
    tagHelperRunner
    -0.50
    makeText
    -0.49
     témoig
    -0.48
    POSITIVE LOGITS
     first
    0.34
    qua
    0.34
     opening
    0.32
    opening
    0.31
     архивлан
    0.31
    ophylla
    0.30
    philis
    0.30
    แรก
    0.30
    DebuggerNonUser
    0.30
     initially
    0.30
    Act Density 0.007%

    No Known Activations