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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

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

    thank you Val

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.53
    XmlAccessorType
    -0.51
    TagMode
    -0.50
    -0.44
    gres
    -0.41
    Geograf
    -0.41
    Revenir
    -0.41
    хьтан
    -0.40
    principalTable
    -0.39
    HomeAsUp
    -0.39
    POSITIVE LOGITS
     awesome
    0.49
     friend
    0.45
     amazing
    0.40
     ritrov
    0.40
     wonderful
    0.39
     acuer
    0.39
    Izvori
    0.39
     wonderfully
    0.39
     Freundin
    0.38
    vgili
    0.38
    Act Density 0.030%

    No Known Activations