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

    Neuronpedia

    INDEX
    Explanations

    expressions of indifference or skepticism towards others' opinions and feelings

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

    expressed care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.56
    principalTable
    -0.52
    InputBorder
    -0.51
     succes
    -0.48
    MLLoader
    -0.48
    :✨
    -0.48
     InputDecoration
    -0.47
    DockStyle
    -0.47
     Signalez
    -0.47
    BufferException
    -0.46
    POSITIVE LOGITS
     care
    0.67
    Care
    0.66
     Care
    0.62
    care
    0.61
     cares
    0.60
     caring
    0.57
    Caring
    0.56
     CARE
    0.55
     Caring
    0.54
     peduli
    0.53
    Act Density 0.033%

    No Known Activations