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

    Neuronpedia

    INDEX
    Explanations

    references to legal charges and judicial processes

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

    charges and accusations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.45
    GraphicsUnit
    -0.44
     Paglinawan
    -0.42
     rospy
    -0.40
    RTEX
    -0.40
    LookAnd
    -0.39
    WriteBarrier
    -0.38
    GEBURTSDATUM
    -0.38
    ADATA
    -0.37
     BrowserModule
    -0.37
    POSITIVE LOGITS
     charges
    0.73
    Charges
    0.66
     Charges
    0.65
     charge
    0.60
     обви
    0.53
     accusations
    0.52
    charges
    0.52
     criminal
    0.52
     allegations
    0.52
     accusation
    0.51
    Act Density 0.600%

    No Known Activations