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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusion or participation in a group or set

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

    both in parallel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.41
     الرياضيه
    -0.41
    HandlerContext
    -0.40
    VolleyError
    -0.39
    ChromeDriver
    -0.36
    DockStyle
    -0.35
     band
    -0.34
     kasarigan
    -0.34
    XtraReports
    -0.34
    UserScript
    -0.33
    POSITIVE LOGITS
     ujednoznacz
    0.66
     myſelf
    0.60
    ffions
    0.57
    ftances
    0.56
    üyada
    0.54
    ftant
    0.53
    ſelves
    0.53
    ðsíða
    0.52
     pouvoit
    0.52
     esternos
    0.52
    Act Density 0.116%

    No Known Activations