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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representation in context

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

    mathematical sequences and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     délais
    -0.39
     fédé
    -0.38
     informée
    -0.38
    tyfik
    -0.36
     над
    -0.35
    aktery
    -0.35
     temporada
    -0.35
     jotka
    -0.35
     delay
    -0.34
     böl
    -0.34
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.61
    fjspx
    0.52
    bootstrapcdn
    0.51
    帖最后由
    0.47
    цездатний
    0.47
    hicles
    0.47
     ©️
    0.46
    +:+
    0.45
     kaarangay
    0.43
    Autoritní
    0.42
    Act Density 0.910%

    No Known Activations