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

    Neuronpedia

    INDEX
    Explanations

    interactions among individuals in a relationship context

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

    actions following names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.69
     zatrzy
    -0.56
     landings
    -0.54
    évaluateur
    -0.54
    expandindo
    -0.52
     landing
    -0.52
    salle
    -0.51
     incontr
    -0.51
    Occurred
    -0.51
    nthetic
    -0.51
    POSITIVE LOGITS
     move
    0.68
     moved
    0.63
    jspx
    0.59
    IUrlHelper
    0.59
     MaterialApp
    0.58
    SpringRunner
    0.57
     Moved
    0.56
    IVEREF
    0.55
     Move
    0.54
     moves
    0.54
    Act Density 0.085%

    No Known Activations