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

    Neuronpedia

    INDEX
    Explanations

    temporal references and indications of recent or ongoing changes

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

    current time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.86
     EconPapers
    -0.84
     AssemblyTitle
    -0.84
     fashiola
    -0.83
    <unused52>
    -0.83
    <unused3>
    -0.83
    <unused23>
    -0.82
    <unused28>
    -0.82
    <unused14>
    -0.82
    <unused8>
    -0.82
    POSITIVE LOGITS
     hacerlo
    0.40
     actualidad
    0.36
     ausencia
    0.34
     now
    0.34
     resistencia
    0.34
     moindre
    0.33
     mejorado
    0.33
     embarazada
    0.33
     involucrados
    0.32
     ninguno
    0.32
    Act Density 0.045%

    No Known Activations