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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and formal entities

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

    office, controller, volume, Kathy, Nathan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.61
     Exactos
    -0.54
    UnsafeEnabled
    -0.53
    Aholisi
    -0.53
    
    -0.51
     kasarigan
    -0.49
    HostException
    -0.47
    XtraEditors
    -0.47
     Signalez
    -0.47
     محفوظة
    -0.46
    POSITIVE LOGITS
     Prag
    0.42
    evalu
    0.40
    Design
    0.40
    UnifiedTopology
    0.40
     Design
    0.40
     Planning
    0.40
    dure
    0.39
     Community
    0.39
    eval
    0.39
     Evaluation
    0.38
    Act Density 0.054%

    No Known Activations